Files
ik_llama.cpp/examples/llama-bench/llama-bench.cpp
saood06 a366a3d17d Load all MoE experts during warmup and make warmup 1 token (#198)
* Load all MoE experts during warmup

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

* Unify warmup to one token

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2025-02-10 17:40:38 +02:00

58 KiB