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

1c27c46
6de3f6a
support compressed-tensors refactor (#1595)
Xin He committed 8 months ago
19b5237
fix CUDA UT for 0.12.0 (#1600)
Xin He committed 8 months ago
7da8ae0
Update ipex backend to be deprecated. (#1599)
Xin He committed 8 months ago
88824a1
fix contiguous issue (#1594)
Xin He committed 8 months ago
4689e93
Revert "add rtn quant func (#1564)" (#1593)
Wang, Mengni committed 8 months ago
d02b2ed
79fa1a9
Support GLM-Image model quantizaiton (#1512)
Liang Lv committed 8 months ago
62f92d1
6bfe88f
Add Performance Test (#1561)
Sun, Xuehao committed 8 months ago
29f0275
Enable CUDA CI (#1473)
Sun, Xuehao committed 8 months ago
4f1a8de
update awq backend infos, refine UT (#1581)
Weiwei committed 8 months ago
06dfc83
disable torch compile for gguf with alg_ext (#1582)
Wenhua Cheng committed 8 months ago
fcb0d2d
add rtn quant func (#1564)
Wang, Mengni committed 8 months ago
1ff8d02
92f0aaa
Refine CPU RAM offload strategy (#1544)
Liang Lv committed 8 months ago
c37add6
Refine model save folder name (#1549)
Tang Kaihui committed 8 months ago
68d5568
4cc0cce
91af35f