mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-28 02:11:50 +00:00
* iq1_m: make it work for QK_K = 64 (WIP) * iq1_m: make it work for QK_K = 64 (scalar and AVX2) * iq1_m: QK_K = 64 seems to work on Metal and ARM_NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
130 KiB
130 KiB