ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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;
return;
}
#endif __CUDA_ARCH__ == GGML_CUDA_CC_TURING
#endif // __CUDA_ARCH__ == GGML_CUDA_CC_TURING
static_assert(!mla || DKQ >= DV, "MLA needs DKQ >= DV");