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

better help printing information (#883)
Heng Guo committed 1 year ago
1b804be
Add GPT-OSS quant support (#887)
Yi Liu committed 1 year ago
081c92a
db560e0
fix vlm gguf ut (#895)
Heng Guo committed 1 year ago
65b7ec2
Fix rtn tuning_device issue (#893)
Tang Kaihui committed 1 year ago
7beac1b
update require accelerate version (#888)
Heng Guo committed 1 year ago
747b7af
[pre-commit.ci] pre-commit autoupdate (#868)
pre-commit-ci[bot] committed 1 year ago
f2b9aef
restrict accelerate version (#885)
Wenhua Cheng committed 1 year ago
d058912
Fix act calibration bug (#880)
Wang, Mengni committed 1 year ago
b693a2a
fp8 exporting bugfix (#874)
Weiwei committed 1 year ago
f56804a
Support Flux quantization (#850)
Wang, Mengni committed 1 year ago
752b2f2
Optimize CPU unit test workflow (#881)
Sun, Xuehao committed 1 year ago
6e567b7
fix vllm backend evaluation (#872)
Xin He committed 1 year ago
5e22944
fix device bug (#873)
Xin He committed 1 year ago
eb5cdcd
7210791
fix FP8 model as input and backend issue (#864)
Wenhua Cheng committed 1 year ago
7b8e280
raise vlm loading error (#863)
Wenhua Cheng committed 1 year ago
ab94a4b
fix bug of get_layer_names_in_block (#861)
Wenhua Cheng committed 1 year ago
25d3044
fix save_quantied format cheaker (#857)
Weiwei committed 1 year ago
780091d
fix bug of data_type fp8_sym (#855)
Heng Guo committed 1 year ago
ba42398
27074ba
fix parse layer config bug (#856)
Wenhua Cheng committed 1 year ago
58d31fc
Add typo checker (#846)
Sun, Xuehao committed 1 year ago
9d2ee69
fix device_map setting (#854)
Tang Kaihui committed 1 year ago
4bb944f
change the method of detecting linear (#849)
Heng Guo committed 1 year ago
3437e3a
fix extra config (#847)
Heng Guo committed 1 year ago
70233bc
NVFP4 Loading support (#839)
Yi Liu committed 1 year ago
0751337