@inproceedings{zhang-etal-2025-dovetail,
    title = "Dovetail: A {CPU}/{GPU} Heterogeneous Speculative Decoding for {LLM} inference",
    author = "Zhang, Libo  and
      Zhang, Zhaoning  and
      Xubaizhou  and
      Li, Rui  and
      Tian, Zhiliang  and
      Mei, Songzhu  and
      Li, Dongsheng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-main.879/",
    doi = "10.18653/v1/2025.emnlp-main.879",
    pages = "17393--17406",
    ISBN = "979-8-89176-332-6"
}