6 Commits

Author	SHA1	Message	Date
humu789	dcf7bfa1a2	[Feature] Add GPTQ and uniform interfaces (#538) ... * add gptq implementation * pre-checkout * passed resnet example * passed llama example * aglin gptq acc * add activation quantization * uniform interfaces * add gptq readme * update mmrazor_large redame * add gptq opt example * fix sparse_gpt example for opt * fix import Protocol from py37 * fix error function name * fix bug in test * fix bug * fix bug * limit sparsegpt test with torch>=1.12 * add docstring for gptq and sparse_gpt * pre-commit * align acc & add save load ckpt & add ut * fix ut * fix ut * fix ut * fix ut & add torch2.0 for ci * del torch2.0 for ci * fix ut --------- Co-authored-by: FIRST_NAME LAST_NAME <MY_NAME@example.com>	2023-05-24 16:38:51 +08:00
LKJacky	7586af005b	move folders and update readme (#528) ... * move folders * update readme --------- Co-authored-by: liukai <your_email@abc.example>	2023-04-26 16:08:54 +08:00
LKJacky	1fbd8726e4	refine sparse gpt (#526) ... * save cpu memory * update * update * update * update * refine * update * update --------- Co-authored-by: Your Name <you@example.com>	2023-04-26 15:55:14 +08:00
LKJacky	595849b912	refine sparse gpt, support multiple gpus with fsdp (#520) ... * add mmrazor large * update readme * add fsdp for opt * update * update * rename * update args * support fsdp * refine * refine * refine * refine * fix out of memorry bug --------- Co-authored-by: liukai <your_email@abc.example> Co-authored-by: Your Name <you@example.com>	2023-04-23 17:03:01 +08:00
LKJacky	bb4e3a956e	enhence sparsegpt (#505) ... * update * fix bug * fix bug * update opt * add memory efficient forward for opt * support to set device for pruning --------- Co-authored-by: liukai <your_email@abc.example> Co-authored-by: Your Name <you@example.com>	2023-04-12 17:55:43 +08:00
LKJacky	316977b036	add sparse gpt (#499) ... init Co-authored-by: liukai <your_email@abc.example>	2023-04-11 16:14:35 +08:00