]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 278d0e1)
llama : use F32 precision in Qwen2 attention and no FA (#8412)
authorGeorgi Gerganov <redacted>
Thu, 11 Jul 2024 07:21:30 +0000 (10:21 +0300)
committerGitHub <redacted>
Thu, 11 Jul 2024 07:21:30 +0000 (10:21 +0300)
commit7a221b672e49dfae459b1af27210ba3f2b5419b6
tree45ce1406db327b0eeb8a593e87612893a68aac56tree
parent278d0e18469aacf505be18ce790a63c7cc31be26commit | diff
llama : use F32 precision in Qwen2 attention and no FA (#8412)
src/llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp