@inproceedings{tao-etal-2025-moqae,
    title = "{M}o{QAE}: Mixed-Precision Quantization for Long-Context {LLM} Inference via Mixture of Quantization-Aware Experts",
    author = "Tao, Wei  and
      Lu, Haocheng  and
      Qu, Xiaoyang  and
      Zhang, Bin  and
      Lu, Kai  and
      Wan, Jiguang  and
      Wang, Jianzong",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.531/",
    pages = "10810--10820",
    ISBN = "979-8-89176-251-0"
}