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
fix several regressions including lm-head quantization, 3bit asym torch backend,etc (#796)
08d6b9e Wenhua Cheng committed 1 year ago
rename llmcompressor to llm_compressor for align with other formats (#780)
e66652a Weiwei committed 1 year ago
fix bug and add nvfp in alg-ext with slight improvement (#794)
7e014ca Wenhua Cheng committed 1 year ago
fix alg_ext regression and support mxfp4 in it with slight improvement (#785)
ca3f733 Wenhua Cheng committed 1 year ago
[API CHANGE] Stage 1 add quant scheme and consolidate device and device_map (#774)
8bcf7ea Wenhua Cheng committed 1 year ago
Keep the model’s buffer dtype unchanged in most cases (#770)
b2c7a3d Wenhua Cheng committed 1 year ago
refine code and fix activation quantization eval regression (#762)
305923b Wenhua Cheng committed 1 year ago
api support for fp8 model and mllm api support load from str (#752)
fcbcaa4 Heng Guo committed 1 year ago