@inproceedings{wang-etal-2026-hqekv,
    title = "{H}qe{KV}: Towards Hybrid Quantization and Eviction for {KV} Cache in Long-Context {LLM} Inference",
    author = "Wang, He  and
      Gu, Yu  and
      Li, Fangfang  and
      Wang, Zhigang  and
      Liu, Zhenghao  and
      Wang, Ning  and
      Li, Xiaohua  and
      Yu, Ge",
    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.201/",
    pages = "4138--4153",
    ISBN = "979-8-89176-395-1"
}