@inproceedings{he-etal-2024-chess,
    title = "{CHESS}: Optimizing {LLM} Inference via Channel-Wise Thresholding and Selective Sparsification",
    author = "He, Junhui  and
      Wu, Shangyu  and
      Wen, Weidong  and
      Xue, Chun Jason  and
      Li, Qingan",
    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/jlcl-multiple-ingestion/2024.emnlp-main.1038/",
    doi = "10.18653/v1/2024.emnlp-main.1038",
    pages = "18658--18668"
}