InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization 文章

ArXiv CS.AI2026-05-27NEWSen作者: Ke Li, Dong An, Xiaoling Zang, Can Ye, Liang Xie, Qibo Qiu, Chen Shen, Xiaofei He, Wenxiao Wang

查看原文 →

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization · 相关技术

相关技术

ODE LLM language model 后训练 UCT SUL Referring expression comprehension (REC)Parts-of-Speech (POS) tags PPR ORM Layout-as-Policy LMM For FFI Effort Metric Attention ARG ANN API