llama.cpp b11006

hexagon: Support for K-Quants Q4_K and Q6_K ( #28994 ) implement q6k/q4k kernels Squashed from: feat: implement q6k kernel hex-q6k: improve unpack…

hexagon: Support for K-Quants Q4_K and Q6_K ( #28994 ) implement q6k/q4k kernels Squashed from: feat: implement q6k kernel hex-q6k: improve unpack accuracy hex-q4_k: add support for Q4_K kernels Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com Website: https://llama.app…

Read the original source — github.com

release · Shared by tscosj

0 comments

No comments yet.