CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-11 10:36:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* vulkan: fix shmem overrun in mmq id shader

* metal : fix mul_mm_id

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ruben Ortlam
2025-10-31 08:14:49 +01:00
committed by GitHub
parent 13002a0896
commit d2a2673dd1
4 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
View File

@@ -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];

2
ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl
View File

@@ -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;