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

c53611f
fix qwen35 regression (#2352)
Wenhua Cheng committed 2 months ago
141e4c9
Update README.md (#2343)
Wenhua Cheng committed 2 months ago
5100390
585d206
32369a6
fix nemoron gate inference issue (#2325)
Wenhua Cheng committed 2 months ago
0ea7c93
reduce cuda ut runing time (#2266)
Heng Guo committed 2 months ago
bdb0d31
de801f9
b4dc0cc
Optimize diffusion calibration step sampling (#2265)
Wang, Chang committed 2 months ago
ce90add
add sdxl svdquant (#2251)
Wang, Chang committed 2 months ago
1c3a551
fix: handle mantissa round overflow (#2302)
Xin He committed 2 months ago
9478fcf
1f23576
Fix xpu CI retry issue (#2309)
chen, suyue committed 2 months ago
fee969d