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

fix cuda ut fail (#1370)
Heng Guo committed 9 months ago
6cdef7a
Disable replace `FP8Expert` (#1379)
Yi Liu committed 9 months ago
137da55
fix --device_map cuda and xpu issue (#1383)
Wenhua Cheng committed 9 months ago
f132c0c
93f7703
Standardize comment language in utils.py (#1378)
Shanto Islam committed 9 months ago
108f2b5
Fix FP8 MLA (#1343)
Yi Liu committed 9 months ago
db77f3b
fix copy python file issue (#1372)
Wenhua Cheng committed 9 months ago
29956d9
add support for w4a16_mixed (#1326)
Heng Guo committed 9 months ago
7cff6af
fix cuda ut fail for transformers v5.0 (#1357)
Heng Guo committed 9 months ago
eb2ccdc
fix bug of exporting fp8 static (#1361)
Heng Guo committed 9 months ago
b04f69c
Autoround in vLLM Office Hours (#1322)
Yi Liu committed 9 months ago
b3f6f1f
Fix cpu ut for transformers v5 (#1333)
Tang Kaihui committed 9 months ago
f6e7e30
Fix CPU CI (#1344)
Sun, Xuehao committed 9 months ago
8eec5d8
add copilot-instructions (#1341)
Xin He committed 9 months ago
0fe5c0a
refactor eval and add UT (#1324)
Xin He committed 9 months ago
14eacb1
Add Chinese README (#1335)
ZaneMark committed 9 months ago
71b385d
Fix attribute bug for diffusion model (#1338)
Wang, Mengni committed 9 months ago
a4ee3a0
update release package and bump version (#1327)
chen, suyue committed 9 months ago
0070219
format add check for scheme args (#1332)
Heng Guo committed 9 months ago
7f1dee6