thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

CUDA: fix FA kernel selection logic (#21271)

Browse source
This commit is contained in:
Johannes Gäßler 2026-04-01 21:28:19 +02:00 • committed by GitHub
parent 6de97b9d3e
commit 86221cf6da
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml/src/ggml-cuda/fattn.cu
View file

@ -340,7 +340,14 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
case 128:
case 112:
case 256:
if (V->ne[0] != K->ne[0]) {
return BEST_FATTN_KERNEL_NONE;
}
break;
case 512:
if (V->ne[0] != K->ne[0]) {
return BEST_FATTN_KERNEL_NONE;
}
if (!gqa_opt_applies) {
return BEST_FATTN_KERNEL_NONE;
}