From: Ruben Ortlam <redacted>
Date: Fri, 31 Oct 2025 07:14:49 +0000 (+0100)
Subject: vulkan: fix shmem overrun in mmq id shader (llama/16873)
X-Git-Tag: upstream/1.8.3~388
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=7ed570ee9471468378a117eeaa96c40db9ac192f;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

vulkan: fix shmem overrun in mmq id shader (llama/16873)

* vulkan: fix shmem overrun in mmq id shader

* metal : fix mul_mm_id

---------

Co-authored-by: Georgi Gerganov <redacted>
---

diff --git a/ggml/src/ggml-metal/ggml-metal-device.cpp b/ggml/src/ggml-metal/ggml-metal-device.cpp
index 1a3c7873..5607deaf 100644
--- a/ggml/src/ggml-metal/ggml-metal-device.cpp
+++ b/ggml/src/ggml-metal/ggml-metal-device.cpp
@@ -677,7 +677,7 @@ ggml_metal_pipeline_t ggml_metal_library_get_pipeline_mul_mm_id_map0(ggml_metal_
     char name[256];
 
     snprintf(base, 256, "kernel_mul_mm_id_map0_ne20_%d", ne20);
-    snprintf(name, 256, "%s", base);
+    snprintf(name, 256, "%s_ne02=%d", base, ne02);
 
     ggml_metal_pipeline_t res = ggml_metal_library_get_pipeline(lib, name);
     if (res) {
diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
index 8b238ac4..d955b4fc 100644
--- a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
@@ -82,9 +82,13 @@ layout (constant_id = 10) const uint WARP = 32;
 
 #include "mul_mmq_shmem_types.glsl"
 
+#ifdef MUL_MAT_ID
+#define BK_STEP 1
+#else
 #ifndef BK_STEP
 #define BK_STEP 4
 #endif
+#endif
 
 // Shared memory cache
 shared block_a_cache buf_a[BM * BK_STEP];
diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl
index 72fec440..1c0f5306 100644
--- a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl
@@ -27,7 +27,7 @@ struct block_a_cache {
 #elif defined(DATA_A_Q8_0)
 #define QUANT_R_MMQ 1
 // AMD likes 4, Intel likes 1 and Nvidia likes 2
-#define BK_STEP 1
+// #define BK_STEP 1
 struct block_a_cache {
     int32_t qs[32/4];
     FLOAT_TYPE dm;