Skip to content

vulkan: fix shmem overrun in mmq id shader #16873

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
0cc4m merged 2 commits into from
Oct 31, 2025
Merged

vulkan: fix shmem overrun in mmq id shader #16873

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c9d7147
vulkan: fix shmem overrun in mmq id shader
0cc4m Oct 30, 2025
dfd8ec0
metal : fix mul_mm_id
ggerganov Oct 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ggml/src/ggml-metal/ggml-metal-device.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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) {
Expand Down
4 changes: 4 additions & 0 deletions ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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];
Expand Down
2 changes: 1 addition & 1 deletion ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand Down
3 changes: 3 additions & 0 deletions tests/test-backend-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6880,6 +6880,9 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 1, 1, false, 8, 16, 1));
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 16, 16, false, 32, 32, 32, 3));

// gpt-oss issue with Vulkan mmq_id
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_MXFP4, GGML_TYPE_F32, 32, 2, false, 2880, 32, 2880));

for (ggml_type type_a : base_types) {
for (ggml_type type_b : {GGML_TYPE_F32 /*, GGML_TYPE_F16 */}) {
for (int n_mats : {4, 8}) {
Expand Down
Loading