@inproceedings{bhendawade-etal-2025-speculative,
    title = "Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention",
    author = "Bhendawade, Nikhil  and
      Belousova, Irina  and
      Fu, Qichen  and
      Mason, Henry  and
      Lin, Antonie  and
      Rastegari, Mohammad  and
      Najibi, Mahyar",
    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/ingest-emnlp/2025.emnlp-main.986/",
    pages = "19547--19570",
    ISBN = "979-8-89176-332-6"
}