]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)
authorIvan Komarov <redacted>
Mon, 17 Apr 2023 13:10:57 +0000 (15:10 +0200)
committerGitHub <redacted>
Mon, 17 Apr 2023 13:10:57 +0000 (15:10 +0200)
commitf266259ad9a2bce5a34d919592310147af23f3dc
tree34744366054065b866d972834bc3787217099e1a
parent47f61aaa5f76d04286792e2fbd0c95b659ab2af0
Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)
CMakeLists.txt
ggml.c
ggml.h
llama.cpp