【论文笔记】AWQ• 文章名称:AWQ:Activation-aware Weight Quantization for LLM Compression and Acceleration • 发表会议/年份:MLSys 2024 • 作者:Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang • 单位:MIT, SJTU, NVIDIA, Tsinghua MIT-IBM, UMass2025-01-06LLM