@inproceedings{wang-etal-2025-bitnet,
    title = "Bitnet.cpp: Efficient Edge Inference for Ternary {LLM}s",
    author = "Wang, Jinheng  and
      Zhou, Hansong  and
      Song, Ting  and
      Cao, Shijie  and
      Xia, Yan  and
      Cao, Ting  and
      Wei, Jianyu  and
      Ma, Shuming  and
      Wang, Hongyu  and
      Wei, Furu",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.457/",
    pages = "9305--9322",
    ISBN = "979-8-89176-251-0"
}