@inproceedings{ning-etal-2025-efficient,
    title = "Efficient Inference for Large Language Models {--}Algorithm, Model, and System",
    author = "Ning, Xuefei  and
      Dai, Guohao  and
      Bai, Haoli  and
      Hou, Lu  and
      Wang, Yu",
    editor = "Pyatkin, Valentina  and
      Vlachos, Andreas",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-tutorials.1/",
    pages = "1--3",
    ISBN = "979-8-89176-336-4"
}