]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: ecd5d6b)
CUDA: enable Gemma FA for HIP/Pascal (#9581)
authorJohannes Gäßler <redacted>
Sun, 22 Sep 2024 07:34:52 +0000 (09:34 +0200)
committerGitHub <redacted>
Sun, 22 Sep 2024 07:34:52 +0000 (09:34 +0200)
commita5b57b08ce1998f7046df75324e86b9e2561c7af
tree3cd06d4ef1c0de575602b6dc122db7f393d97f71tree
parentecd5d6b65be08927e62de1587d5fd22778cdc250commit | diff
CUDA: enable Gemma FA for HIP/Pascal (#9581)
ggml/src/ggml-cuda.cu diff | blob | history
ggml/src/ggml-cuda/fattn.cu diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp