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
add pile calib, rename quant_block_list to to_quant_block_names (#322)
d493572 WeiweiZhang1 committed 2 years ago
better align gradient_accumulate_steps for varied length input (#309)
103e7e6 wenhuach21 committed 2 years ago
refine model config file for mixed precision quantization (#300)
fccae4b wenhuach21 committed 2 years ago
use torch.compile by default for PyTorch versions 2.6 and above (#295)
c922f5b wenhuach21 committed 2 years ago
[Experimental Feature]support for common hf multimodel (#276)
e643212 n1ck-guo committed 2 years ago