b6490
llama-bench: add --n-cpu-moe support (#15952) * llama-bench: add --n-cpu-moe support Support --n-cpu-moe in llama-bench the same way it is supported by llama-server.
llama-bench: add --n-cpu-moe support (#15952) * llama-bench: add --n-cpu-moe support Support --n-cpu-moe in llama-bench the same way it is supported by llama-server.