mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-04-20 05:26:07 +00:00

* multi row k quant shaders! * better row selection * more row choices * readjust row selection * rm_kq=2 by default
* multi row k quant shaders! * better row selection * more row choices * readjust row selection * rm_kq=2 by default