Files
llama.cpp/ggml-metal.m
Kawrakow 27ad57a69b Metal: faster Q4_0 and Q4_1 matrix x vector kernels (#2212)
* 3-5% faster Q4_0 on Metal

* 7-25% faster Q4_1 on Metal

* Oops, forgot to delete the original Q4_1 kernel

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-07-14 11:46:21 +02:00

49 KiB