@inproceedings{devoto-etal-2024-simple,
    title = "A Simple and Effective $L\_2$ Norm-Based Strategy for {KV} Cache Compression",
    author = "Devoto, Alessio  and
      Zhao, Yu  and
      Scardapane, Simone  and
      Minervini, Pasquale",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.1027/",
    doi = "10.18653/v1/2024.emnlp-main.1027",
    pages = "18476--18499"
}