mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
* metal : fix kernel_norm ggml-ci * metal : put warning in kernel_norm to not combine the loops * metal : restore original F16 mat-vec multiplication It works after the norm fixes * common : don't do warm-up with more than n_batch tokens (close #3058) ggml-ci * metal : minor