From: Jeff Bolz <redacted>
Date: Tue, 26 Nov 2024 15:45:05 +0000 (-0600)
Subject: vulkan: fix group_norm (llama/10496)
X-Git-Tag: upstream/1.7.4~145
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=5e1fcc1780bdc713caf0fb0566f5357235d16fe1;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

vulkan: fix group_norm (llama/10496)

Fix bad calculation of the end of the range. Add a backend test that
covers the bad case (taken from stable diffusion).

Fixes https://github.com/leejet/stable-diffusion.cpp/issues/439.
---

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 49527fdf..da1cfd24 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -7157,7 +7157,7 @@ static void ggml_vk_check_results_0(ggml_tensor * tensor) {
         const int32_t max_period = tensor->op_params[1];
         tensor_clone = ggml_timestep_embedding(ggml_ctx, src0_clone, dim, max_period);
     } else if (tensor->op == GGML_OP_POOL_2D) {
-        enum ggml_op_pool op = static_cast<ggml_op_pool>(dst->op_params[0]);
+        enum ggml_op_pool op = static_cast<ggml_op_pool>(tensor->op_params[0]);
         const int32_t k0 = tensor->op_params[1];
         const int32_t k1 = tensor->op_params[2];
         const int32_t s0 = tensor->op_params[3];
diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/group_norm.comp b/ggml/src/ggml-vulkan/vulkan-shaders/group_norm.comp
index 5ad9b28d..b6a0d564 100644
--- a/ggml/src/ggml-vulkan/vulkan-shaders/group_norm.comp
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/group_norm.comp
@@ -19,7 +19,7 @@ void main() {
 
     const uint tid = gl_LocalInvocationID.x;
     const uint start = gl_WorkGroupID.x * group_size + tid;
-    const uint end = start + group_size;
+    const uint end = (gl_WorkGroupID.x + 1) * group_size;
 
     tmp[tid] = 0.0f;