vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-10 04:00:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

occam patch for vulkan: fix shmem overrun in mmq id shader https://github.com/ggml-org/llama.cpp/pull/16873

Browse source
This commit is contained in:
Concedo 2025-10-31 10:58:29 +08:00
parent 2b00e55356
commit adec6eb5d5
3 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-metal/ggml-metal-device.cpp
View file

@ -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) {

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;