tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix typo in FlashAttention code (#13926)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-05-30 21:22:03 +02:00
committed by GitHub
parent b47ab7b8e9
commit e562eece7c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-mma-f16.cuh
View File

@ -1246,7 +1246,7 @@ static __global__ void flash_attn_ext_f16(
NO_DEVICE_CODE; NO_DEVICE_CODE;
return; return;
} }
#endif __CUDA_ARCH__ == GGML_CUDA_CC_TURING #endif // __CUDA_ARCH__ == GGML_CUDA_CC_TURING
static_assert(!mla || DKQ >= DV, "MLA needs DKQ >= DV"); static_assert(!mla || DKQ >= DV, "MLA needs DKQ >= DV");