@inproceedings{sharma-etal-2025-minikv,
    title = "{M}ini{KV}: Pushing the Limits of 2-Bit {KV} Cache via Compression and System Co-Design for Efficient Long Context Inference",
    author = "Sharma, Akshat  and
      Ding, Hangliang  and
      Li, Jianping  and
      Dani, Neel  and
      Zhang, Minjia",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.952/",
    pages = "18506--18523",
    ISBN = "979-8-89176-256-5"
}