]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix FlashAttention on Turing (#13415)
authorJohannes Gäßler <redacted>
Sat, 10 May 2025 07:16:52 +0000 (09:16 +0200)
committerGitHub <redacted>
Sat, 10 May 2025 07:16:52 +0000 (09:16 +0200)
commitd8919424f1dee7dc1638349c616f2ef5d2ee16fb
tree60bd518feadf0590b6b144e7e1962dd6aa69ee6e
parent7fef11766cdeb9fa7bbbe3db13580616b7d3d599
CUDA: fix FlashAttention on Turing (#13415)
ggml/src/ggml-cuda/fattn-mma-f16.cuh