vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-16 19:59:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

fix bad merge

Browse source
This commit is contained in:
Concedo 2026-05-15 22:47:24 +08:00
parent 35f524d3e2
commit 74c6daba1a
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-cuda/fattn.cu
View file

@ -479,6 +479,12 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
return BEST_FATTN_KERNEL_MMA_F16;
}
const int ncols2_max = Q->ne[0] == 320 ? 32 : ((Q->ne[0] == 576 || Q->ne[0] == 192) ? 16 : 8);
int gqa_ratio_eff = 1;
while (gqa_ratio % (2*gqa_ratio_eff) == 0 && gqa_ratio_eff < ncols2_max) {
gqa_ratio_eff *= 2;
}
// Use the WMMA kernel if possible but only for HIP
#if defined(GGML_HIP_ROCWMMA_FATTN)
if (ggml_cuda_should_use_wmma_fattn(cc) && K->ne[1] % FATTN_KQ_STRIDE == 0 && Q->ne[0] != 40 && Q->ne[0] != 72 && Q->ne[0] != 192 && Q->ne[0] != 512 && Q->ne[0] != 576) {