llama.cpp
8fcb5636 - Load all MoE experts during warmup (#11571)

Commit
180 days ago
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 <sszymczy@gmail.com>
Author
Parents
Loading