@inproceedings{liu-etal-2024-unlocking-data,
    title = "Unlocking Data-free Low-bit Quantization with Matrix Decomposition for {KV} Cache Compression",
    author = "Liu, Peiyu  and
      Gao, Ze-Feng  and
      Zhao, Xin  and
      Ma, Yipeng  and
      Wang, Tao  and
      Wen, Ji-Rong",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-long.133/",
    doi = "10.18653/v1/2024.acl-long.133",
    pages = "2430--2440"
}