@inproceedings{liu-etal-2023-llm,
    title = "{LLM}-{FP}4: 4-Bit Floating-Point Quantized Transformers",
    author = "Liu, Shih-yang  and
      Liu, Zechun  and
      Huang, Xijie  and
      Dong, Pingcheng  and
      Cheng, Kwang-Ting",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.39/",
    doi = "10.18653/v1/2023.emnlp-main.39",
    pages = "592--605"
}