@inproceedings{jiang-etal-2026-towards,
    title = "Towards Efficient Large Language Model Serving: A Survey on System-Aware {KV} Cache Optimization",
    author = "Jiang, Jiantong  and
      Yang, Peiyu  and
      Zhang, Rui  and
      Liu, Feng",
    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.1916/",
    pages = "38450--38476",
    ISBN = "979-8-89176-395-1"
}