@inproceedings{lu-etal-2024-xinference,
    title = "Xinference: Making Large Model Serving Easy",
    author = "Lu, Weizheng  and
      Xiong, Lingfeng  and
      Zhang, Feng  and
      Qin, Xuye  and
      Chen, Yueguo",
    editor = "Hernandez Farias, Delia Irazu  and
      Hope, Tom  and
      Li, Manling",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2024.emnlp-demo.30/",
    doi = "10.18653/v1/2024.emnlp-demo.30",
    pages = "291--300"
}