@inproceedings{hu-etal-2025-stitchllm,
    title = "{S}titch{LLM}: Serving {LLM}s, One Block at a Time",
    author = "Hu, Bodun  and
      Li, Shuozhe  and
      Agarwal, Saurabh  and
      Lee, Myungjin  and
      Jajoo, Akshay  and
      Li, Jiamin  and
      Xu, Le  and
      Kim, Geon-Woo  and
      Kim, Donghyun  and
      Xu, Hong  and
      Zhang, Amy  and
      Akella, Aditya",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1305/",
    pages = "26887--26903",
    ISBN = "979-8-89176-251-0"
}