7 commits

Author	SHA1	Message	Date
lunar	618a5f50ee	Add transpose operator when replace Conv1d with qlinear_cuda_old	2023-06-05 23:11:18 +08:00
qwopqwop200	f4820f2988	change qlinear cuda support 64dim	2023-06-03 07:30:34 +09:00
qwopqwop200	2df7d7105d	support 64 cuda dim	2023-06-02 19:54:37 +09:00
qwopqwop200	33809a8e59	remove log	2023-05-30 23:51:39 +09:00
qwopqwop200	dfd9dc0e6b	change if trainable backend pytorch	2023-05-30 23:43:55 +09:00
PanQiWei	2b532f9453	add trainable mode	2023-05-26 13:11:30 +08:00
PanQiWei	cfd27e8caa	refactor file structure of qlinears	2023-05-26 07:18:16 +08:00

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