@inproceedings{jo-etal-2026-fastkv,
    title = "{F}ast{KV}: Decoupling of Context Reduction and {KV} Cache Compression for Prefill-Decoding Acceleration",
    author = "Jo, Dongwon  and
      Song, Jiwon  and
      Kim, Yulhwa  and
      Kim, Jae-Joon",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1610/",
    pages = "32167--32186",
    ISBN = "979-8-89176-395-1"
}