EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

CUDA: fix Volta FlashAttention logic (#11615)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-03 13:25:56 +01:00
committed by GitHub
parent d92cb67e37
commit 21c84b5d2d
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-wmma-f16.cu
View File

@@ -561,7 +561,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_ten
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
break;
// case 256:
// ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
// ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, float>(ctx, dst);
// break;
default:
GGML_ABORT("fatal error");