@inproceedings{ashkboos-etal-2024-quik,
    title = "{QUIK}: Towards End-to-end 4-Bit Inference on Generative Large Language Models",
    author = "Ashkboos, Saleh  and
      Markov, Ilia  and
      Frantar, Elias  and
      Zhong, Tingxuan  and
      Wang, Xincheng  and
      Ren, Jie  and
      Hoefler, Torsten  and
      Alistarh, Dan",
    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.197/",
    doi = "10.18653/v1/2024.emnlp-main.197",
    pages = "3355--3371"
}