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 MoE for llama/gpt-oss (#1557)
Yi Liu committed 8 months ago
555052e
Support block-wise fp8 quant (#1487)
Wang, Mengni committed 8 months ago
e660059
fix google/gemma-3-4b-it (#1547)
Xin He committed 8 months ago
b5fc172
Add markdown-link-check (#1531)
Sun, Xuehao committed 8 months ago
50c4c7f
fix alg_ext torch compile issue (#1540)
Wenhua Cheng committed 8 months ago
9d54ddc
Fix sglang ut (#1541)
Wang, Mengni committed 8 months ago
53f2b0e
837888d
a42fd85
fix broken link (#1530)
Xin He committed 8 months ago
f8e8ae9
0d37215
Support diffusion model saving (#1519)
Wang, Mengni committed 8 months ago
a0ad778
e14e7db
enable --eval for diffusion model (#1522)
Xin He committed 8 months ago
eec1bed
0127590
Enable more xpu instance for xpu CI (#1521)
chen, suyue committed 8 months ago
30e4043
fix bug of quantizing Z-image (#1516)
Xin He committed 8 months ago
8a404ec
Fix CUDA UT and HPU UT (#1514)
Sun, Xuehao committed 8 months ago
89f99ae
fix low_gpu default value, refine doc (#1520)
Weiwei committed 8 months ago
279637d
be38713