]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Avoid the transposed X branch in the Z = X * Y matrix multiplication (#439)
authorGeorgi Gerganov <redacted>
Thu, 23 Mar 2023 21:22:01 +0000 (23:22 +0200)
committerGitHub <redacted>
Thu, 23 Mar 2023 21:22:01 +0000 (23:22 +0200)
commit483bab2e3d4a868fe679d8bb32827d2a4df214dc
tree0ae7226ed8874d487ea0dfb7703a05bc11616967
parent404e1da38ec8025707031a8027da14dc1590f952
Avoid the transposed X branch in the Z = X * Y matrix multiplication (#439)

Should make results reproducible for different number of threads and batch sizes
llama.cpp