OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Wenqi Shao, Ping Luo(Wuhan University), Zhiqian Li(Sichuan University), Peng Xu(Chinese Academy of Sciences), Yu Qiao, Zhaoyang Zhang, Peng Gao, Kaipeng Zhang, Lirui Zhao, Mengzhao Chen
arXiv (Cornell University)
August 25, 2023
Cited by 14


Related Papers