ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
e05cca9ef652eee7b42927485a3821b14e3c565f
ik_llama.cpp/iqk_mul_mat.cpp
Iwan Kawrakow e05cca9ef6 bitnet(scale in a separate tensor): CPU improvements 
Arrange Q8 quants in blocks of 128 and adapt iqk_mul_mat
to deal with that. This improves PP speef by a few percent.
2024-06-22 12:02:52 +03:00

193 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink