Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Commits on main

llm_layer_config_bugfix (#406)
WeiweiZhang1 committed 1 year ago
7714796
support for deepseek vl2 (#401)
Heng Guo committed 1 year ago
bf8d68d
fix dtype converting issue (#403)
Wenhua Cheng committed 1 year ago
6ac7a2b
Fix auto-round install & bump into 0.4.4 (#387)
Sun, Xuehao committed 1 year ago
4fd9bbd
fix device auto issue (#400)
Wenhua Cheng committed 1 year ago
73fcf7d
fix seqlen issue (#399)
WeiweiZhang1 committed 1 year ago
d06546a
support awq format for vlms (#398)
WeiweiZhang1 committed 1 year ago
c82aa88
vlm 70B+ in single card (#395)
Heng Guo committed 1 year ago
42a6eb9
3dd8ae6
34fc38e
update eval basic usage (#384)
Heng Guo committed 1 year ago
6cead7d
refine homepage, update model links (#385)
WeiweiZhang1 committed 1 year ago
2a8573d
support_llava_hf_vlm_example (#381)
WeiweiZhang1 committed 1 year ago
e6f89d1
bump version into v0.4.2 (#379)
Sun, Xuehao committed 1 year ago
2990616
fix typos (#377)
Wenhua Cheng committed 1 year ago
dba15cf
fix gpu ut (#376)
Heng Guo committed 1 year ago
2ffadfd
Add gpu ut (#370)
Wenhua Cheng committed 1 year ago
ecc17be
save processor automatically (#372)
Heng Guo committed 1 year ago
e4528e9
fix bias issue in autogptq (#375)
Wenhua Cheng committed 1 year ago
3ac377b
[HPU] Add lazy mode back (#371)
Yi Liu committed 1 year ago
7acb784
quant_block_names enhancement (#369)
WeiweiZhang1 committed 1 year ago
67281e2
b2944b9
add gpu test (#367)
Wenhua Cheng committed 1 year ago
1a250eb
fix awq exporting bugs (#365)
Wenhua Cheng committed 1 year ago
d080ea0
fix awq backend and fp_layers issue (#363)
Wenhua Cheng committed 1 year ago
9b9eeb6