]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Load all MoE experts during warmup (#11571)
authorfairydreaming <redacted>
Fri, 14 Mar 2025 12:47:05 +0000 (13:47 +0100)
committerGitHub <redacted>
Fri, 14 Mar 2025 12:47:05 +0000 (13:47 +0100)
commit8fcb563613e20a04dd9791f0a9b8a41086428c09
treed799428c90de9b3ca10da3c7b0c1892e1943a55f
parentadd2a3aa5a1571211aa5c7303b8e80c8d1824b91
Load all MoE experts during warmup (#11571)

* llama : introduce llama_set_warmup() API call that controls warmup mode; use all MoE experts during warmup

* common : use new API to enable warmup mode during model warmup

---------

Co-authored-by: Stanisław Szymczyk <redacted>
common/common.cpp
include/llama.h
src/llama-context.cpp
src/llama-context.h
src/llama-cparams.h
src/llama-graph.cpp