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
mllm supports loading fp8 model and fix bug of loading fp8 model (#750)
c1e719b Heng Guo committed 1 year ago
Fix torch_zp infer bug & API disable_deterministic_algorithms bug (#733)
71dab1d Weiwei committed 1 year ago
add original convert file and support for the newest llama.cpp (#729)
2acf786 Heng Guo committed 1 year ago
make the tuning deterministic and move infrequently used arguments to kwargs (#726)
478aedb Wenhua Cheng committed 1 year ago
support fp8 model and str as input in llm quantization (#699)
32777f7 Wenhua Cheng committed 1 year ago