mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
* iq2xs: faster AVX2 dot product * iq2xs: small AVX2 imrovement * Speed up computing sign bits in AVX2 iq2_xs dot product --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> Co-authored-by: Peter Reid <peter@peterreid.net>
392 KiB
392 KiB