public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-12 01:05:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

HIP: avoid treating CDNA as dgx spark for gqa_ratio 20 in fattn_mma dqk 576 (llama/29572)

Browse Source
This commit is contained in:
uvos
2026-10-06 10:38:14 +03:00
committed by Georgi Gerganov
parent b4a085a024
commit 817294a93e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn.cu
+1 -1
View File
@@ -365,7 +365,7 @@ static void ggml_cuda_flash_attn_ext_mma_f16(ggml_backend_cuda_context & ctx, gg
GGML_ASSERT(Q->ne[2] % K->ne[2] == 0);
const int gqa_ratio = Q->ne[2] / K->ne[2];
if (gqa_ratio == 20) { // GLM 4.7 Flash
if (gqa_ratio == 20 && GGML_CUDA_CC_IS_NVIDIA(cc)) { // GLM 4.7 Flash
if (cc >= GGML_CUDA_CC_DGX_SPARK) {
if (Q->ne[1] <= 8) {
ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1<576, 512, 16>(ctx, dst);