@inproceedings{kong-etal-2024-swapmoe,
    title = "{S}wap{M}o{E}: Serving Off-the-shelf {M}o{E}-based Large Language Models with Tunable Memory Budget",
    author = "Kong, Rui  and
      Li, Yuanchun  and
      Feng, Qingtian  and
      Wang, Weijun  and
      Ye, Xiaozhou  and
      Ouyang, Ye  and
      Kong, Linghe  and
      Liu, Yunxin",
    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://aclanthology.org/2024.acl-long.363/",
    doi = "10.18653/v1/2024.acl-long.363",
    pages = "6710--6720"
}