@inproceedings{tao-etal-2025-asymkv,
    title = "{A}sym{KV}: Enabling 1-Bit Quantization of {KV} Cache with Layer-Wise Asymmetric Quantization Configurations",
    author = "Tao, Qian  and
      Yu, Wenyuan  and
      Zhou, Jingren",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.158/",
    pages = "2316--2328"
}