]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : use F32 precision in GLM4 attention and no FA (#9130)
authorpiDack <redacted>
Fri, 23 Aug 2024 07:27:17 +0000 (15:27 +0800)
committerGitHub <redacted>
Fri, 23 Aug 2024 07:27:17 +0000 (10:27 +0300)
commita07c32ea54850c989f0ef6989da5b955b77b7172
treea2657d3af2d64295736c753181969469c520df10
parent11b84eb4578864827afcf956db5b571003f18180
llama : use F32 precision in GLM4 attention and no FA (#9130)
src/llama.cpp