@inproceedings{hooper-etal-2025-squeezed,
    title = "Squeezed Attention: Accelerating Long Context Length {LLM} Inference",
    author = "Hooper, Coleman Richard Charles  and
      Kim, Sehoon  and
      Mohammadzadeh, Hiva  and
      Maheswaran, Monishwaran  and
      Zhao, Sebastian  and
      Paik, June  and
      Mahoney, Michael W.  and
      Keutzer, Kurt  and
      Gholami, Amir",
    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.1568/",
    pages = "32631--32652",
    ISBN = "979-8-89176-251-0"
}