tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 05:33:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

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
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);