@inproceedings{fang-etal-2026-zserve,
    title = "{ZSERVE}: An Adaptive Framework for Optimizing Large Language Models Serving in Heterogeneous Infrastructures",
    author = "Fang, Taosong  and
      Ma, Zhengzhao  and
      Chen, Jiawei  and
      Yang, Yushen  and
      Zhou, Kaijie  and
      Zheng, Jia  and
      Han, Xianpei  and
      Sun, Le  and
      Lin, Hongyu  and
      Lu, Yaojie",
    editor = "Agrawal, Sweta  and
      Abad, Alberto",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-demos.33/",
    pages = "330--337",
    ISBN = "979-8-89176-461-3"
}