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
Bump protobuf from 3.20.1 to 3.20.2 in /test/test_cuda (#585)
dc6d389 dependabot[bot] committed 1 year ago
modify default asym 4bits auto-round format to awq, fix save folder typo for mllm (#575)
c1c8148 Weiwei committed 1 year ago
refine xpu requirement/config json and fix several issues (#558)
a45eadb Wenhua Cheng committed 1 year ago
[GGUF STEP4] fix search bug and improve packing & eval speed (#545)
4b85b51 Heng Guo committed 1 year ago