@inproceedings{ma-etal-2024-hpipe,
    title = "{HP}ipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective Devices",
    author = "Ma, Ruilong  and
      Yang, Xiang  and
      Wang, Jingyu  and
      Qi, Qi  and
      Sun, Haifeng  and
      Wang, Jing  and
      Zhuang, Zirui  and
      Liao, Jianxin",
    editor = "Yang, Yi  and
      Davani, Aida  and
      Sil, Avi  and
      Kumar, Anoop",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.naacl-industry.1/",
    doi = "10.18653/v1/2024.naacl-industry.1",
    pages = "1--9"
}