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

[mllm] support longcat_next (#1637)
Xin He committed 7 months ago
0821817
Fix omni model test CI issue (#1667)
Liang Lv committed 7 months ago
bbda404
Update unit test requirements (#1670)
Sun, Xuehao committed 7 months ago
440faaf
Enhance performance test (#1610)
Sun, Xuehao committed 7 months ago
5b0d3fa
[pre-commit.ci] pre-commit autoupdate (#1661)
pre-commit-ci[bot] committed 7 months ago
e4f9493
force auto-scheme low_gpu to True in CLI (#1653)
Wenhua Cheng committed 7 months ago
0f7dba7
Correct docstring (#1652)
Yi Liu committed 7 months ago
de0650e
Refine CI (#1644)
Sun, Xuehao committed 7 months ago
9f54985
update xpu quantization cost (#1618)
Xin He committed 7 months ago
e18a625
Bump main branch version to v0.13.0 (#1639)
chen, suyue committed 7 months ago
59c20f5
Fix group_size issue (#1638)
Wang, Mengni committed 7 months ago
7b0ff41
Update torch to 2.11.0 in CI (#1606)
Sun, Xuehao committed 7 months ago
ae7661b
fix CI for transformers==5.4.0 (#1627)
Xin He committed 7 months ago
5a38a39
refine transform config api. (#1607)
lkk committed 7 months ago
f07048b
fix rtn bug (#1622)
Wenhua Cheng committed 7 months ago
891cf6e
fix fp8 accuracy drop issue (#1611)
Wang, Mengni committed 7 months ago
b78453c
fix diffusion model tuning issue (#1617)
Wang, Mengni committed 7 months ago
e56369c