mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-28 05:30:58 -05:00
* 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