@inproceedings{liu-etal-2024-vptq,
    title = "{VPTQ}: Extreme Low-bit Vector Post-Training Quantization for Large Language Models",
    author = "Liu, Yifei  and
      Wen, Jicheng  and
      Wang, Yang  and
      Ye, Shengyu  and
      Zhang, Li Lyna  and
      Cao, Ting  and
      Li, Cheng  and
      Yang, Mao",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.467/",
    doi = "10.18653/v1/2024.emnlp-main.467",
    pages = "8181--8196"
}