@inproceedings{gokhale-etal-2026-kv,
    title = "{KV} {P}areto: Systems-Level Optimization of {KV} Cache and Model Compression for Long Context Inference",
    author = "Gokhale, Sai  and
      Das, Devleena  and
      Patwari, Rajeev  and
      Sirasao, Ashish  and
      Delaye, Elliott",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.9/",
    pages = "119--131",
    ISBN = "979-8-89176-384-5"
}