vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

CUDA: enable Gemma FA for HIP/Pascal (#9581)

Browse source
This commit is contained in:
Johannes Gäßler 2024-09-22 09:34:52 +02:00 • committed by GitHub
parent ecd5d6b65b
commit a5b57b08ce
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 12 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn.cu
View file

@ -314,7 +314,7 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
}
if (!fast_fp16_available(cc)) {
if (Q->ne[1] <= 8) {
if (Q->ne[1] <= 8 || Q->ne[0] == 256) {
ggml_cuda_flash_attn_ext_vec_f32(ctx, dst);
} else {
ggml_cuda_flash_attn_ext_tile_f32(ctx, dst);