@inproceedings{li-etal-2022-easy,
    title = "Easy and Efficient Transformer: Scalable Inference Solution For Large {NLP} Model",
    author = "Li, Gongzheng  and
      Xi, Yadong  and
      Ding, Jingzhen  and
      Wang, Duan  and
      Luo, Ziyang  and
      Zhang, Rongsheng  and
      Liu, Bai  and
      Fan, Changjie  and
      Mao, Xiaoxi  and
      Zhao, Zeng",
    editor = "Loukina, Anastassia  and
      Gangadharaiah, Rashmi  and
      Min, Bonan",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
    month = jul,
    year = "2022",
    address = "Hybrid: Seattle, Washington + Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-industry.8/",
    doi = "10.18653/v1/2022.naacl-industry.8",
    pages = "62--68"
}