webgpu : add CONV_2D_DW (depthwise conv2d) kernel (#25847)

* webgpu : add CONV_2D_DW (depthwise conv2d) kernel

Implement GGML_OP_CONV_2D_DW for the WebGPU backend,
ported from the Vulkan backend's conv2d_dw.comp.

Assisted-by: Claude Opus-4.8
* Remove unnecessary comments in webgpu support

* update supported ops tables, triggered by adding webgpu CONV_2D_DW

diff --git a/docs/ops.md b/docs/ops.md
index c5601523697d2aa0115412fc4596bfd0559ace60..557b1a023d2eabedfcb0b82ade4d8193e20e87a4 100644 (file)
--- a/docs/ops.md
+++ b/docs/ops.md
@@ -25,10 +25,10 @@ Legend:
 |                             CEIL | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                            CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | 🟡 | ✅ | ❌ | ❌ |
 |                        COL2IM_1D | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
-|                           CONCAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                           CONCAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                             CONT | ❌ | 🟡 | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                          CONV_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                       CONV_2D_DW | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9d\8c | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9d\8c | ❌ | ❌ |
+|                       CONV_2D_DW | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9d\8c | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9c\85 | ❌ | ❌ |
 |                          CONV_3D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
 |                CONV_TRANSPOSE_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                CONV_TRANSPOSE_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
@@ -41,6 +41,9 @@ Legend:
 |                             DIAG | ❌ | ❌ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                    DIAG_MASK_INF | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                              DIV | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                     DSV4_HC_COMB | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+|                     DSV4_HC_POST | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+|                      DSV4_HC_PRE | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 |                              DUP | ❌ | ✅ | ✅ | 🟡 | ❌ | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                              ELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                              EXP | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -63,16 +66,17 @@ Legend:
 |                        HARDSWISH | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                           IM2COL | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                        IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
-|                          L2_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                          L2_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                       LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ❌ | ✅ | 🟡 | ❌ | ❌ | ❌ |
+|                LIGHTNING_INDEXER | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 |                              LOG | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             MEAN | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                              MUL | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                          MUL_MAT | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 |
-|                 MUL_MAT_HADAMARD | â\9d\8c | â\9d\8c | â\9d\8c | â\9d\8c | â\9c\85 | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9d\8c | ❌ | ❌ |
+|                 MUL_MAT_HADAMARD | â\9d\8c | â\9d\8c | â\9d\8c | â\9d\8c | â\9c\85 | â\9d\8c | â\9d\8c | â\9c\85 | â\9c\85 | â\9c\85 | ❌ | ❌ |
 |                       MUL_MAT_ID | ❌ | 🟡 | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | 🟡 | 🟡 | ❌ |
 |                              NEG | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                             NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ |
+|                             NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ❌ |
 |                   OPT_STEP_ADAMW | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
 |                     OPT_STEP_SGD | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
 |                         OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | ❌ | ❌ | ❌ | 🟡 |
@@ -82,7 +86,7 @@ Legend:
 |                          POOL_2D | ❌ | 🟡 | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                            REGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             RELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                           REPEAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                           REPEAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                      REPEAT_BACK | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                         RMS_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                    RMS_NORM_BACK | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |

diff --git a/docs/ops/WebGPU.csv b/docs/ops/WebGPU.csv
index 95042e72d9c12c17b8f951f6e9a2c08d8455d4b3..c19396c03e4dee6d6c1d9133d094834756003f73 100644 (file)
--- a/docs/ops/WebGPU.csv
+++ b/docs/ops/WebGPU.csv
@@ -167,6 +167,16 @@
 "WebGPU: WebGPU","ROUND","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","TRUNC","type=f32,ne_a=[128,2,2,2],v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","TRUNC","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_COMB","n_tokens=1,n_iter=1,eps=0.000001","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_COMB","n_tokens=17,n_iter=4,eps=0.000001","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_COMB","n_tokens=257,n_iter=8,eps=0.000001","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_PRE","n_embd=1,n_tokens=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_PRE","n_embd=31,n_tokens=17","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_PRE","n_embd=128,n_tokens=257","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_PRE","n_embd=4096,n_tokens=21","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_POST","n_embd=1,n_tokens=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_POST","n_embd=31,n_tokens=17","support","0","no","WebGPU"
+"WebGPU: WebGPU","DSV4_HC_POST","n_embd=128,n_tokens=257","support","0","no","WebGPU"
 "WebGPU: WebGPU","REGLU","type=f16,ne_a=[128,2,2,2],v=0,swapped=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REGLU","type=f16,ne_a=[5,7,11,13],v=0,swapped=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REGLU","type=f16,ne_a=[128,2,2,2],v=0,swapped=1","support","1","yes","WebGPU"
@@ -338,14 +348,18 @@
 "WebGPU: WebGPU","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=1,be2=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=1,be2=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=7,be2=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=7,be2=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=1,be2=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=1,be2=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=7,be2=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=7,be2=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=1,be2=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GET_ROWS","type=nvfp4,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=q2_K,n=256,m=5,r=4,be1=1,be2=1,v=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=q2_K,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=q2_K,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","WebGPU"
@@ -407,6 +421,7 @@
 "WebGPU: WebGPU","GET_ROWS","type=i32,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS","type=i32,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=f32,n=1,m=8,r=2,b=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS_BACK","type=f32,n=1,m=70000,r=4,b=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=f16,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
@@ -425,6 +440,8 @@
 "WebGPU: WebGPU","GET_ROWS_BACK","type=q8_0,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=q1_0,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=q1_0,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS_BACK","type=q2_0,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","GET_ROWS_BACK","type=q2_0,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=mxfp4,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=mxfp4,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=nvfp4,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
@@ -459,333 +476,685 @@
 "WebGPU: WebGPU","GET_ROWS_BACK","type=iq4_xs,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=i32,n=256,m=5,r=4,b=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","GET_ROWS_BACK","type=i32,n=256,m=5,r=4,b=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i32,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i32,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=0","support","0","no","WebGPU"
@@ -965,6 +1334,7 @@
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[3000,384,1,1],ne_kernel=[3,384,384,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=3,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
@@ -974,6 +1344,7 @@
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=3,d1=0,is_2D=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f16,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
@@ -1050,6 +1421,8 @@
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,2,2560],ne_kernel=[3,3,2,2560],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[5,5,1,32],ne_kernel=[3,4,1,32],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[2,2,1536,729],ne_kernel=[2,2,1536,4096],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[128,128,1,2],ne_kernel=[32,33,1,2],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[128,128,2,1],ne_kernel=[33,34,2,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","IM2COL_3D","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","IM2COL_3D","type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","IM2COL_3D","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0","support","0","no","WebGPU"
@@ -4669,10 +5042,16 @@
 "WebGPU: WebGPU","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f32,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f16,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f32,stride=1,padding=0,dilation=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f32,stride=1,padding=0,dilation=1,cwhn=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f32,stride=2,padding=1,dilation=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f32,stride=2,padding=1,dilation=1,cwhn=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f16,stride=1,padding=0,dilation=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f16,stride=1,padding=0,dilation=1,cwhn=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f16,stride=2,padding=1,dilation=1,cwhn=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f16,stride=2,padding=1,dilation=1,cwhn=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","WebGPU"
@@ -5047,6 +5426,39 @@
 "WebGPU: WebGPU","CONV_TRANSPOSE_1D","ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=1,p0=0,d0=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_TRANSPOSE_1D","ne_input=[3,2,1,1],ne_kernel=[3,1,2,1],s0=1,p0=0,d0=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_TRANSPOSE_1D","ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=16,OC=32,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=4,OC=3,T_in=7,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=1,OC=5,T_in=13,s0=1,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=6,OC=4,T_in=11,s0=3,p0=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=2,OC=3,T_in=9,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=5,OC=4,T_in=11,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=8,OC=4,T_in=13,s0=4,p0=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=4,OC=3,T_in=1,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=16,OC=1,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=1,OC=5,T_in=13,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f32,K=8,OC=2,T_in=3,s0=2,p0=5","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=16,OC=32,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=4,OC=3,T_in=7,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=1,OC=5,T_in=13,s0=1,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=6,OC=4,T_in=11,s0=3,p0=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=2,OC=3,T_in=9,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=5,OC=4,T_in=11,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=8,OC=4,T_in=13,s0=4,p0=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=4,OC=3,T_in=1,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=16,OC=1,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=1,OC=5,T_in=13,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=f16,K=8,OC=2,T_in=3,s0=2,p0=5","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=16,OC=32,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=4,OC=3,T_in=7,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=1,OC=5,T_in=13,s0=1,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=6,OC=4,T_in=11,s0=3,p0=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=2,OC=3,T_in=9,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=5,OC=4,T_in=11,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=8,OC=4,T_in=13,s0=4,p0=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=4,OC=3,T_in=1,s0=2,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=16,OC=1,T_in=197,s0=8,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=1,OC=5,T_in=13,s0=3,p0=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","COL2IM_1D","type=bf16,K=8,OC=2,T_in=3,s0=2,p0=5","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[3,2,3,1],ne_kernel=[2,2,1,3],stride=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[10,10,9,1],ne_kernel=[3,3,1,9],stride=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[129,63,35,1],ne_kernel=[3,3,48,35],stride=1","support","0","no","WebGPU"
@@ -5069,6 +5481,7 @@
 "WebGPU: WebGPU","REPEAT","type=f32,ne=[10,5,4,1],nr=[1,1,1,2]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=i32,ne=[10,5,4,1],nr=[2,1,1,1]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=i16,ne=[10,5,4,1],nr=[1,1,1,2]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","REPEAT","type=bf16,ne=[10,5,4,1],nr=[2,1,1,1]","support","0","no","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,1,1,1]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=f32,ne=[10,5,4,3],nr=[2,1,1,1]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,2,1,1]","support","1","yes","WebGPU"
@@ -5076,6 +5489,7 @@
 "WebGPU: WebGPU","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,1,1,2]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=i32,ne=[10,5,4,3],nr=[2,1,1,1]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","REPEAT","type=i16,ne=[10,5,4,3],nr=[1,1,1,2]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","REPEAT","type=bf16,ne=[10,5,4,3],nr=[2,1,1,1]","support","0","no","WebGPU"
 "WebGPU: WebGPU","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[1,1,1,1],v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[2,1,1,1],v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[1,2,1,1],v=0","support","0","no","WebGPU"
@@ -5108,449 +5522,568 @@
 "WebGPU: WebGPU","SET","type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=2,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SET","type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=3,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SET","type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=3,inplace=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[384,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[384,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne=[384,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[192,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[192,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne=[192,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q1_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=nvfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=nvfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q1_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=nvfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=nvfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q1_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q1_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=nvfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=nvfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=i32,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=i32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=i32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=i32,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,4,3,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=i32,type_dst=i32,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=i32,type_dst=i32,ne=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
-"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=q4_1,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=q5_0,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=q5_1,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=q8_0,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[192,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[192,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=nvfp4,ne_src=[192,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=q2_K,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=q3_K,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=q4_K,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=q5_K,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=q6_K,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=iq2_xxs,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=iq2_xs,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=iq2_s,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=iq3_xxs,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=iq1_s,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=iq1_m,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=iq4_nl,ne_src=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=iq3_s,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=iq4_xs,ne_src=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=bf16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=bf16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q8_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=nvfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q3_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q6_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_m,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_nl,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_nl,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q8_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=nvfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q3_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q6_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_m,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_nl,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_nl,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=bf16,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=bf16,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_1,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_1,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q8_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=nvfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q2_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q3_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q3_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q4_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q5_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q6_K,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=q6_K,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq2_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_xxs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_xxs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_m,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq1_m,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_nl,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_nl,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_s,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq3_s,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_xs,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=iq4_xs,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_1,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_1,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q8_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q1_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=mxfp4,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=nvfp4,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q2_K,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q3_K,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_K,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q5_K,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q6_K,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xxs,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_xs,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq2_s,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_xxs,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_s,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq1_m,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_nl,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq3_s,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=iq4_xs,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f32,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f16,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=i32,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=i32,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=i32,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=i32,type_dst=f32,ne_src=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,4,3,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[256,4,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=bf16,type_dst=bf16,ne_src=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=i32,type_dst=i32,ne_src=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=i32,type_dst=i32,ne_src=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[2,2097121,1,1],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[2,2,524281,1],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[128,2,3,1],ne_dst=[128,2,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0,dst_alloc=[128,4,3,1]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[128,2,3,1],ne_dst=[128,2,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0,dst_alloc=[128,4,3,1]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,7,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,32,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,32,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,7,5,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,7,5,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,7,32,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,7,32,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,32,5,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,32,5,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,32,7,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[3,32,7,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,3,7,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,3,7,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,3,32,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,3,32,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,7,3,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,7,3,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,7,32,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,7,32,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,32,3,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,32,3,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,32,7,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[5,32,7,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,3,5,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,3,5,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,3,32,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,3,32,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,5,3,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,5,3,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,5,32,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,5,32,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,32,3,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,32,3,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,32,5,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[7,32,5,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,3,5,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,3,5,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,3,5,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,3,7,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,3,7,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,3,7,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,5,3,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,5,3,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,5,3,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,5,7,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,5,7,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,5,7,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,7,3,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,7,3,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,7,3,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f32,type_dst=f32,ne_src=[32,7,5,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=q4_0,type_dst=q4_0,ne_src=[32,7,5,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,5,7,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,5,32,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,5,32,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,7,5,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,7,5,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,7,32,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,7,32,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,32,5,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,32,5,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,32,7,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[3,32,7,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,3,7,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,3,7,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,3,32,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,3,32,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,7,3,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,7,3,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,7,32,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,7,32,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,32,3,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,32,3,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,32,7,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[5,32,7,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,3,5,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,3,5,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,3,32,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,3,32,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,5,3,32],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,5,3,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,5,32,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,5,32,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,32,3,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,32,3,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,32,5,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[7,32,5,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,3,5,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,3,5,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,3,7,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,3,7,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,5,3,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,5,3,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,5,7,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,5,7,3],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,7,3,5],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,7,3,5],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CPY","type_src=f16,type_dst=f16,ne_src=[32,7,5,3],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONT","type=f32,ne=[2,1,1,1],use_view_slice=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONT","type=f32,ne=[2,1,3,5],use_view_slice=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONT","type=f32,ne=[2,3,5,7],use_view_slice=1","support","1","yes","WebGPU"
@@ -5952,76 +6485,96 @@
 "WebGPU: WebGPU","SCALE","type=f32,ne=[10,10,10,10],scale=2.000000,bias=1.000000,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SCALE","type=f32,ne=[100,10,10,10],scale=2.000000,bias=1.000000,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SILU_BACK","type=f32,ne=[64,5,4,3],eps=0.000001","support","0","no","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000001","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000001","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000100","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000100","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.100000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.100000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=10.000000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0,noncontig_rows=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,inplace=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000,noncontig_rows=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=10.000000","support","0","no","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=1,noncontig_rows=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0,noncontig_rows=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SSM_CONV","type=f32,ne_a=[3,1024,1,1],ne_b=[3,1024,1,1]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","SSM_CONV","type=f32,ne_a=[6,1024,1,1],ne_b=[3,1024,1,1]","support","1","yes","WebGPU"
@@ -6084,6 +6637,12 @@
 "WebGPU: WebGPU","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4","support","0","no","WebGPU"
 "WebGPU: WebGPU","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=64,n=1,k=64,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=256,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=512,n=1,k=512,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=32,k=128,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=4,k=128,bs=[2,3],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6165,6 +6724,15 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6174,15 +6742,15 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q2_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q2_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q2_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6309,6 +6877,9 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6318,6 +6889,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6330,6 +6902,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6345,6 +6918,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6357,6 +6931,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6376,6 +6951,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6388,6 +6964,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6403,6 +6980,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6415,6 +6993,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6434,6 +7013,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6446,6 +7026,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6461,6 +7042,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6473,6 +7055,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6492,6 +7075,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6504,6 +7088,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6519,6 +7104,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6531,6 +7117,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6550,6 +7137,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6562,6 +7150,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6581,6 +7170,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6593,6 +7183,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6612,6 +7203,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6624,6 +7216,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6643,6 +7236,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6655,6 +7249,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6665,6 +7260,72 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6674,6 +7335,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6686,6 +7348,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6705,6 +7368,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6717,6 +7381,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6736,6 +7401,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6748,6 +7414,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6767,6 +7434,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6779,6 +7447,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6798,6 +7467,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6810,6 +7480,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6829,6 +7500,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6841,6 +7513,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6860,6 +7533,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6872,6 +7546,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6891,6 +7566,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6903,6 +7579,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6913,37 +7590,39 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6953,6 +7632,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -6965,6 +7645,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -6984,6 +7665,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -6996,6 +7678,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","WebGPU"
@@ -7015,6 +7698,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
@@ -7027,6 +7711,7 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
@@ -7037,6 +7722,15 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=bf16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q5_0,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -7082,8 +7776,9 @@
 "WebGPU: WebGPU","MUL_MAT","type_a=q5_1,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q8_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q1_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=q2_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=mxfp4,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT","type_a=nvfp4,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q2_K,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q3_K,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT","type_a=q4_K,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","WebGPU"
@@ -7491,6 +8186,33 @@
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=16,n_used=16,b=1,m=50,n=200,k=64","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=1,n_used=1,b=0,m=8,n=16,k=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=32,n_used=2,b=0,m=2880,n=32,k=2880","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=32,n_used=2,b=0,m=2880,n=32,k=2880","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q5_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q5_1,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=384","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=192","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=192","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q3_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q5_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q6_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq3_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq1_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq1_m,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq4_nl,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq3_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=iq4_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
@@ -7779,6 +8501,78 @@
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
@@ -8067,78 +8861,78 @@
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","0","no","WebGPU"
-"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","0","no","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","WebGPU"
+"WebGPU: WebGPU","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","WebGPU"
 "WebGPU: WebGPU","MUL_MAT_ID","type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","WebGPU"
@@ -8759,6 +9553,134 @@
 "WebGPU: WebGPU","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","WebGPU"
@@ -9527,6 +10449,13 @@
 "WebGPU: WebGPU","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[8,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[16,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[32,1],nr=[1,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[8,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[16,1],trans_b=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[32,1],trans_b=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=32","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=129","support","1","yes","WebGPU"
@@ -9946,6 +10875,11 @@
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,16,2,1],n_dims=128,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[16,16,8192,1],n_dims=16,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
@@ -10000,126 +10934,281 @@
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,16,2,1],n_dims=128,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[16,16,8192,1],n_dims=16,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","ROPE","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
@@ -10174,6 +11263,11 @@
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,16,2,1],n_dims=128,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[16,16,8192,1],n_dims=16,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
@@ -10228,126 +11322,281 @@
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,16,2,1],n_dims=128,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[16,16,8192,1],n_dims=16,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f32,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=8,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=40,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","ROPE_BACK","type=f16,ne_a=[36,16,2457,1],n_dims=36,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=2,inplace=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f32,ne_a=[128,32,2,3],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1,inplace=1","support","1","yes","WebGPU"
@@ -10409,37 +11658,197 @@
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ROPE","type=f16,ne_a=[128,32,2,3],n_dims=128,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","WebGPU"
 "WebGPU: WebGPU","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","0","no","WebGPU"
+"WebGPU: WebGPU","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","0","no","WebGPU"
 "WebGPU: WebGPU","ARGSORT","type=f32,ne=[3,1,1,1],order=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ARGSORT","type=f32,ne=[4,1,1,1],order=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","ARGSORT","type=f32,ne=[7,1,1,1],order=0","support","1","yes","WebGPU"
@@ -10901,6 +12310,19 @@
 "WebGPU: WebGPU","PAD","type=f32,ne_a=[512,512,1,1],pad_0=1,pad_1=1,circular=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","PAD","type=f32,ne_a=[33,17,2,1],pad_0=4,pad_1=3,circular=1","support","1","yes","WebGPU"
 "WebGPU: WebGPU","PAD","type=f32,ne_a=[512,512,3,1],lp0=1,rp0=1,lp1=1,rp1=1,lp2=1,rp2=1,lp3=1,rp3=1,tfrm=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1024,1,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1024,2,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1024,16,1,1],pad_0=0,pad_1=1,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1023,1,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1023,8,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1025,1,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[1025,8,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[2048,1,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[2048,4,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[2049,1,1,1],pad_0=1,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[100,1,1,1],pad_0=100,pad_1=0,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[100,1,1,1],pad_0=0,pad_1=100,circular=0","support","1","yes","WebGPU"
+"WebGPU: WebGPU","PAD","type=f32,ne_a=[100,100,1,1],pad_0=50,pad_1=50,circular=0","support","1","yes","WebGPU"
 "WebGPU: WebGPU","PAD_REFLECT_1D","type=f32,ne_a=[512,34,2,1],pad_0=10,pad_1=9","support","0","no","WebGPU"
 "WebGPU: WebGPU","PAD_REFLECT_1D","type=f32,ne_a=[3000,384,4,1],pad_0=10,pad_1=9","support","0","no","WebGPU"
 "WebGPU: WebGPU","ROLL","shift0=3,shift1=-2,shift3=1,shift4=-1","support","0","no","WebGPU"
@@ -14998,6 +16420,22 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15014,6 +16452,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15038,6 +16484,22 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15054,6 +16516,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15070,6 +16540,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15086,6 +16564,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[8,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=128,nh=4,nr23=[16,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15110,6 +16596,22 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15126,6 +16628,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15150,6 +16660,22 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,2,1,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15166,6 +16692,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15182,6 +16716,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15198,6 +16740,14 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[8,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=192,hsv=192,nh=4,nr23=[16,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
@@ -15934,10 +17484,11 @@
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
-"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q4_0,permute=[0,1,2,3]","support","0","no","WebGPU"
-"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=f16,permute=[0,1,2,3]","support","0","no","WebGPU"
-"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=96,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q8_0,permute=[0,1,2,3]","support","0","no","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=f16,permute=[0,1,2,3]","support","1","yes","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=96,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=96,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f32,permute=[0,1,2,3]","support","0","no","WebGPU"
+"WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=4,nr23=[1,1],kv=256,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=4,nr23=[1,1],kv=96,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q1_0,type_V=q1_0,permute=[0,1,2,3]","support","0","no","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=128,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q1_0,type_V=q4_0,permute=[0,1,2,3]","support","0","no","WebGPU"
 "WebGPU: WebGPU","FLASH_ATTN_EXT","hsk=64,hsv=128,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q1_0,permute=[0,1,2,3]","support","0","no","WebGPU"
@@ -15948,21 +17499,147 @@
 "WebGPU: WebGPU","CROSS_ENTROPY_LOSS_BACK","type=f32,ne=[30000,1,1,1]","support","0","no","WebGPU"
 "WebGPU: WebGPU","OPT_STEP_ADAMW","type=f32,ne=[10,5,4,3]","support","0","no","WebGPU"
 "WebGPU: WebGPU","OPT_STEP_SGD","type=f32,ne=[10,5,4,3]","support","0","no","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=128,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=1,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=16,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=1,kda=0","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1","support","1","yes","WebGPU"
-"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=128,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=16,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=1,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=64,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=127,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=256,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=65,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=100,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=200,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=127,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=64,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=33,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=100,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=2,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=2","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=128,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=1,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=8,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=3","support","1","yes","WebGPU"
+"WebGPU: WebGPU","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=16,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=iq4_nl","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=f32","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=f16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=bf16","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q8_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q5_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q5_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q4_1","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q4_0","support","0","no","WebGPU"
+"WebGPU: WebGPU","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=iq4_nl","support","0","no","WebGPU"

diff --git a/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp b/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
index d7692363a1dedf93119da6c9c351e9f5b78306bd..bed9265b8ab7c4a98ed50d936c70f6d26e3f311e 100644 (file)
--- a/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
+++ b/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
@@ -355,6 +355,30 @@ struct ggml_webgpu_conv2d_pipeline_key_hash {
     }
 };
 
+// Same type fields as conv2d plus the input layout (WHCN vs CWHN).
+struct ggml_webgpu_conv2d_dw_pipeline_key {
+    ggml_type weight_type;
+    ggml_type input_type;
+    ggml_type output_type;
+    bool      whcn;
+
+    bool operator==(const ggml_webgpu_conv2d_dw_pipeline_key & other) const {
+        return weight_type == other.weight_type && input_type == other.input_type && output_type == other.output_type &&
+               whcn == other.whcn;
+    }
+};
+
+struct ggml_webgpu_conv2d_dw_pipeline_key_hash {
+    size_t operator()(const ggml_webgpu_conv2d_dw_pipeline_key & key) const {
+        size_t seed = 0;
+        ggml_webgpu_hash_combine(seed, key.weight_type);
+        ggml_webgpu_hash_combine(seed, key.input_type);
+        ggml_webgpu_hash_combine(seed, key.output_type);
+        ggml_webgpu_hash_combine(seed, key.whcn);
+        return seed;
+    }
+};
+
 /** Im2Col **/
 struct ggml_webgpu_im2col_pipeline_key {
     ggml_type input_type;
@@ -1210,6 +1234,8 @@ class ggml_webgpu_shader_lib {
         soft_max_pipelines;
     std::unordered_map<ggml_webgpu_conv2d_pipeline_key, webgpu_pipeline, ggml_webgpu_conv2d_pipeline_key_hash>
         conv2d_pipelines;
+    std::unordered_map<ggml_webgpu_conv2d_dw_pipeline_key, webgpu_pipeline, ggml_webgpu_conv2d_dw_pipeline_key_hash>
+        conv2d_dw_pipelines;
     std::unordered_map<ggml_webgpu_im2col_pipeline_key, webgpu_pipeline, ggml_webgpu_im2col_pipeline_key_hash>
         im2col_pipelines;
 
@@ -3172,6 +3198,50 @@ class ggml_webgpu_shader_lib {
         return conv2d_pipelines[key];
     }
 
+    // whcn selects the input layout: contiguous WHCN vs contiguous-channels CWHN
+    webgpu_pipeline get_conv2d_dw_pipeline(const ggml_webgpu_shader_lib_context & context, bool whcn) {
+        ggml_webgpu_conv2d_dw_pipeline_key key = {};
+        key.weight_type                        = context.src0->type;
+        key.input_type                         = context.src1->type;
+        key.output_type                        = context.dst->type;
+        key.whcn                               = whcn;
+
+        auto it = conv2d_dw_pipelines.find(key);
+        if (it != conv2d_dw_pipelines.end()) {
+            return it->second;
+        }
+
+        std::vector<std::string> defines;
+        std::string              variant = whcn ? "conv_2d_dw_whcn" : "conv_2d_dw_cwhn";
+
+        auto push_type_defines = [&](const char * prefix, ggml_type type) {
+            std::string s_prefix = prefix;
+            if (type == GGML_TYPE_F32) {
+                defines.push_back(s_prefix + "_F32");
+            } else if (type == GGML_TYPE_F16) {
+                defines.push_back(s_prefix + "_F16");
+            } else {
+                GGML_ABORT("Unsupported type for CONV_2D_DW shader");
+            }
+        };
+
+        push_type_defines("WEIGHT", key.weight_type);
+        push_type_defines("INPUT", key.input_type);
+        push_type_defines("OUTPUT", key.output_type);
+        if (whcn) {
+            defines.push_back("WHCN");
+        }
+        defines.push_back(std::string("WG_SIZE=") + std::to_string(context.max_wg_size));
+
+        auto processed           = preprocessor.preprocess(wgsl_conv2d_dw, defines);
+        auto decisions           = std::make_shared<ggml_webgpu_generic_shader_decisions>();
+        decisions->wg_size       = context.max_wg_size;
+        webgpu_pipeline pipeline = ggml_webgpu_create_pipeline(device, processed, variant);
+        pipeline.context         = decisions;
+        conv2d_dw_pipelines[key] = pipeline;
+        return conv2d_dw_pipelines[key];
+    }
+
     webgpu_pipeline get_im2col_pipeline(const ggml_webgpu_shader_lib_context & context) {
         ggml_webgpu_im2col_pipeline_key key = {};
         key.input_type                      = context.src1->type;

diff --git a/ggml/src/ggml-webgpu/ggml-webgpu.cpp b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
index 29025e9ba4e391f0ee21376d40a306ed8cf10c8f..75286ec7313cd4ff906b661477f4426490f4b589 100644 (file)
--- a/ggml/src/ggml-webgpu/ggml-webgpu.cpp
+++ b/ggml/src/ggml-webgpu/ggml-webgpu.cpp
@@ -978,6 +978,67 @@ static webgpu_encoded_op ggml_webgpu_conv_2d(webgpu_context & ctx,
     return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
 }
 
+// Same param/binding layout as conv_2d; the shader differs
+static webgpu_encoded_op ggml_webgpu_conv_2d_dw(webgpu_context & ctx,
+                                                ggml_tensor *    src0,
+                                                ggml_tensor *    src1,
+                                                ggml_tensor *    dst) {
+    const int32_t s0 = ggml_get_op_params_i32(dst, 0);
+    const int32_t s1 = ggml_get_op_params_i32(dst, 1);
+    const int32_t p0 = ggml_get_op_params_i32(dst, 2);
+    const int32_t p1 = ggml_get_op_params_i32(dst, 3);
+    const int32_t d0 = ggml_get_op_params_i32(dst, 4);
+    const int32_t d1 = ggml_get_op_params_i32(dst, 5);
+
+    // Scalar params matching conv2d_dw.wgsl (weight src0 [KW,KH,1,C], input src1, output dst).
+    std::vector<uint32_t> params = {
+        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src0) / ggml_type_size(src0->type)),
+        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src1) / ggml_type_size(src1->type)),
+        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
+
+        (uint32_t) ggml_nelements(dst),
+        (uint32_t) dst->ne[2],
+        (uint32_t) dst->ne[3],
+        (uint32_t) dst->ne[0],
+        (uint32_t) dst->ne[1],
+        (uint32_t) src1->ne[0],
+        (uint32_t) src1->ne[1],
+        (uint32_t) src0->ne[0],
+        (uint32_t) src0->ne[1],
+
+        (uint32_t) s0,
+        (uint32_t) s1,
+        (uint32_t) p0,
+        (uint32_t) p1,
+        (uint32_t) d0,
+        (uint32_t) d1,
+    };
+
+    std::vector<wgpu::BindGroupEntry> entries = {
+        ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src0),
+        ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, src1),
+        ggml_webgpu_make_tensor_bind_group_entry(ctx, 2, dst),
+    };
+
+    ggml_webgpu_shader_lib_context shader_lib_ctx = {};
+    shader_lib_ctx.src0                           = src0;
+    shader_lib_ctx.src1                           = src1;
+    shader_lib_ctx.dst                            = dst;
+    shader_lib_ctx.max_wg_size = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
+
+    // Input layout: contiguous -> WHCN, contiguous-channels -> CWHN
+    const bool      whcn      = ggml_is_contiguous(src1);
+    webgpu_pipeline pipeline  = ctx->shader_lib->get_conv2d_dw_pipeline(shader_lib_ctx, whcn);
+    auto *          decisions = static_cast<ggml_webgpu_generic_shader_decisions *>(pipeline.context.get());
+
+    uint32_t wg_x;
+    uint32_t wg_y;
+    uint32_t total_wg = CEIL_DIV((uint32_t) ggml_nelements(dst), decisions->wg_size);
+    compute_2d_workgroups(total_wg, ctx->global_ctx->capabilities.limits.maxComputeWorkgroupsPerDimension, wg_x, wg_y);
+
+    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
+}
+
 static webgpu_encoded_op ggml_webgpu_im2col(webgpu_context & ctx,
                                             ggml_tensor *    src0,
                                             ggml_tensor *    src1,
@@ -3164,6 +3225,8 @@ static std::optional<webgpu_encoded_op> ggml_webgpu_encode(webgpu_context ctx,
             return ggml_webgpu_sum_rows(ctx, src0, node);
         case GGML_OP_CONV_2D:
             return ggml_webgpu_conv_2d(ctx, src0, src1, node);
+        case GGML_OP_CONV_2D_DW:
+            return ggml_webgpu_conv_2d_dw(ctx, src0, src1, node);
         case GGML_OP_IM2COL:
             return ggml_webgpu_im2col(ctx, src0, src1, node);
         case GGML_OP_UPSCALE:
@@ -4349,6 +4412,12 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
                           (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16) &&
                           (src1->type == GGML_TYPE_F32 || src1->type == GGML_TYPE_F16);
             break;
+        case GGML_OP_CONV_2D_DW:
+            supports_op = (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) &&
+                          (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16) &&
+                          (src1->type == GGML_TYPE_F32 || src1->type == GGML_TYPE_F16) &&
+                          (ggml_is_contiguous(src1) || ggml_is_contiguous_channels(src1));
+            break;
         case GGML_OP_IM2COL:
             supports_op = (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) &&
                           (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16);

diff --git a/ggml/src/ggml-webgpu/wgsl-shaders/conv2d_dw.wgsl b/ggml/src/ggml-webgpu/wgsl-shaders/conv2d_dw.wgsl
new file mode 100644 (file)
index 0000000..42d6f02
--- /dev/null
+++ b/ggml/src/ggml-webgpu/wgsl-shaders/conv2d_dw.wgsl
@@ -0,0 +1,137 @@
+#include "common_decls.tmpl"
+enable f16;
+
+// Ported from the Vulkan backend's conv2d_dw.comp. Two variants (based on WHCN)
+// selected by the input (src1) layout: contiguous -> WHCN, else CWHN.
+// weight (src0) is [KW,KH,1,C]; output matches the input layout.
+
+@group(0) @binding(0)
+#if defined(WEIGHT_F32)
+var<storage, read_write> weights: array<f32>;
+#elif defined(WEIGHT_F16)
+var<storage, read_write> weights: array<f16>;
+#endif
+
+@group(0) @binding(1)
+#if defined(INPUT_F32)
+var<storage, read_write> input: array<f32>;
+#elif defined(INPUT_F16)
+var<storage, read_write> input: array<f16>;
+#endif
+
+@group(0) @binding(2)
+#if defined(OUTPUT_F32)
+var<storage, read_write> output: array<f32>;
+#elif defined(OUTPUT_F16)
+var<storage, read_write> output: array<f16>;
+#endif
+
+struct Params {
+    offset_w: u32,
+    offset_i: u32,
+    offset_o: u32,
+
+    ne: u32,
+    channels: u32,
+    batches: u32,
+    dst_w: u32, dst_h: u32,
+    src_w: u32, src_h: u32,
+    knl_w: u32, knl_h: u32,
+
+    stride_x: i32, stride_y: i32,
+    pad_x: i32, pad_y: i32,
+    dilation_x: i32, dilation_y: i32,
+};
+
+@group(0) @binding(3)
+var<uniform> params: Params;
+
+fn load_weight(idx: u32) -> f32 {
+    #if defined(WEIGHT_F32)
+        return weights[idx];
+    #elif defined(WEIGHT_F16)
+        return f32(weights[idx]);
+    #endif
+}
+fn load_input(idx: u32) -> f32 {
+    #if defined(INPUT_F32)
+        return input[idx];
+    #elif defined(INPUT_F16)
+        return f32(input[idx]);
+    #endif
+}
+fn store_output(idx: u32, val: f32) {
+    #if defined(OUTPUT_F32)
+        output[idx] = val;
+    #elif defined(OUTPUT_F16)
+        output[idx] = f16(val);
+    #endif
+}
+
+#if defined(WHCN)
+// Input/output/kernel contiguous in [W, H, C, N] order (kernel [KW,KH,C]).
+fn conv_2d_dw(idx: u32) -> f32 {
+    let i0    = idx / params.dst_w;
+    let dst_x = idx - i0 * params.dst_w;
+    let i1    = i0 / params.dst_h;
+    let dst_y = i0 - i1 * params.dst_h;
+    let n     = i1 / params.channels;
+    let c     = i1 - n * params.channels;
+
+    let src_i = params.offset_i + n * params.channels * params.src_h * params.src_w
+                                + c * params.src_h * params.src_w;
+    let knl_i = params.offset_w + c * params.knl_h * params.knl_w;
+
+    var sum: f32 = 0.0;
+    for (var ky: u32 = 0u; ky < params.knl_h; ky += 1u) {
+        let src_y = i32(dst_y) * params.stride_y + i32(ky) * params.dilation_y - params.pad_y;
+        if (src_y < 0 || src_y >= i32(params.src_h)) { continue; }
+        for (var kx: u32 = 0u; kx < params.knl_w; kx += 1u) {
+            let src_x = i32(dst_x) * params.stride_x + i32(kx) * params.dilation_x - params.pad_x;
+            if (src_x < 0 || src_x >= i32(params.src_w)) { continue; }
+            let v = load_input(src_i + u32(src_y) * params.src_w + u32(src_x));
+            let k = load_weight(knl_i + ky * params.knl_w + kx);
+            sum += v * k;
+        }
+    }
+    return sum;
+}
+#else
+// Channels contiguous (CWHN): channel is the innermost axis.
+fn conv_2d_dw(idx: u32) -> f32 {
+    let i0    = idx / params.channels;
+    let c     = idx - i0 * params.channels;
+    let i1    = i0 / params.dst_w;
+    let dst_x = i0 - i1 * params.dst_w;
+    let n     = i1 / params.dst_h;
+    let dst_y = i1 - n * params.dst_h;
+
+    let src_i   = params.offset_i + n * params.channels * params.src_h * params.src_w;
+    let src_row = params.src_w * params.channels;
+    let knl_row = params.knl_w * params.channels;
+
+    var sum: f32 = 0.0;
+    for (var ky: u32 = 0u; ky < params.knl_h; ky += 1u) {
+        let src_y = i32(dst_y) * params.stride_y + i32(ky) * params.dilation_y - params.pad_y;
+        if (src_y < 0 || src_y >= i32(params.src_h)) { continue; }
+        for (var kx: u32 = 0u; kx < params.knl_w; kx += 1u) {
+            let src_x = i32(dst_x) * params.stride_x + i32(kx) * params.dilation_x - params.pad_x;
+            if (src_x < 0 || src_x >= i32(params.src_w)) { continue; }
+            let v = load_input(src_i + u32(src_y) * src_row + u32(src_x) * params.channels + c);
+            let k = load_weight(params.offset_w + ky * knl_row + kx * params.channels + c);
+            sum += v * k;
+        }
+    }
+    return sum;
+}
+#endif
+
+@compute @workgroup_size(WG_SIZE)
+fn main(
+    @builtin(global_invocation_id) gid: vec3<u32>,
+    @builtin(num_workgroups) num_wg: vec3<u32>
+) {
+    let idx = gid.x + (num_wg.x * u32(WG_SIZE)) * gid.y;
+    if (idx >= params.ne) { return; }
+    store_output(params.offset_o + idx, conv_2d_dw(idx));
+}