intel/auto-round · AI Repo StatsINintel/auto-round
PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Suy luận & chạy LLM cục bộPython Apache-2.0 201tạo 2024-01-04 #diffusers#gguf#int4#llms#mxfp4#nvfp4#omni#quantization#rounding#sglang#transformers#vllm#vlms