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
enhance calibration dataset and add awq pre quantization warning (#396)
01b779c Wenhua Cheng committed 1 year ago
remove the dependency on AutoGPTQ for CPU and bump to V0.4.3 (#380)
3323371 Sun, Xuehao committed 1 year ago
ix incorrect device setting in autoround format inference (#383)
e88882e WeiweiZhang1 committed 1 year ago
fix duplicated block_name_to_quantize exporting in gptq format (#382)
8d8c70d WeiweiZhang1 committed 1 year ago
fix bug of only_text_test check due to inference issue on cpu (#362)
3acb119 Heng Guo committed 1 year ago