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

update doc (#1856)
Wenhua Cheng committed 5 months ago
f06f9a1
fix save_quantized log conflict (#1845)
Weiwei committed 5 months ago
2776198
refine/fix gptq format (#1853)
Wenhua Cheng committed 5 months ago
09ca561
Sage fast sfm (#1843)
Luo Yu committed 5 months ago
d52c2a1
Fix gpt-j-6b RTN RuntimeError (#1848)
Liang Lv committed 5 months ago
28f4238
09bc743
Fix some CI issues (#1842)
Liang Lv committed 6 months ago
fd49549
Support Exporting Block-Wise FP8 AR Format (#1798)
Zhenzhong Xu committed 6 months ago
bf1c81c
64a5817
Awq algorithm (#1749)
Weiwei committed 6 months ago
e8ccff2
add inc integration unit test (#1820)
Xin He committed 6 months ago
948b482
remove new arch warning (#1832)
Heng Guo committed 6 months ago
5ce6308
Fix few merge errors (#1817)
Heng Guo committed 6 months ago
706ac7e
[step2]adjust gguf tuning algorithm (#1824)
Wenhua Cheng committed 6 months ago
10b9f52
add auto_round_rtn cli and remove fast (#1808)
Heng Guo committed 6 months ago
debba75
[step 1]adjust gguf tuning algorithm (#1649)
Wenhua Cheng committed 6 months ago
770b7a3
add smooth K for sagev1 (#1806)
Luo Yu committed 6 months ago
017ed92