]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : do not cap thread count when MoE on CPU (#5419)
authorPaul Tsochantaris <redacted>
Fri, 9 Feb 2024 10:48:06 +0000 (10:48 +0000)
committerGitHub <redacted>
Fri, 9 Feb 2024 10:48:06 +0000 (12:48 +0200)
commite5ca3937c685d6e012ac4db40555d6ec100ff03c
tree9fd9668a2b9774a5602839c6e69a185ad0f44c8c
parente4124c24775f2cb5b3d7acc93bf9dc5471c172ef
llama : do not cap thread count when MoE on CPU (#5419)

* Not capping thread count when MoE inference is running on CPU

* Whitespace
llama.cpp