7 commits

Author	SHA1	Message	Date
qwopqwop200	f4820f2988	change qlinear cuda support 64dim	2023-06-03 07:30:34 +09:00
qwopqwop200	b03f53294f	support 64dim cuda	2023-06-02 19:53:50 +09:00
qwopqwop200	0f2841cb13	remove log	2023-05-30 23:51:55 +09:00
qwopqwop200	5274313067	change if trainable backend pytorch	2023-05-30 23:40:58 +09:00
PanQiWei	2b532f9453	add trainable mode	2023-05-26 13:11:30 +08:00
PanQiWei	69609c4bc7	support faster vecquant4matmul cuda kernel	2023-05-26 08:55:05 +08:00
PanQiWei	cfd27e8caa	refactor file structure of qlinears	2023-05-26 07:18:16 +08:00

Renamed from auto_gptq/nn_modules/qlinear.py (Browse further)