@inproceedings{tuli-etal-2024-dynamo,
    title = "{D}yna{M}o: Accelerating Language Model Inference with Dynamic Multi-Token Sampling",
    author = "Tuli, Shikhar  and
      Lin, Chi-Heng  and
      Hsu, Yen-Chang  and
      Jha, Niraj  and
      Shen, Yilin  and
      Jin, Hongxia",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.182/",
    doi = "10.18653/v1/2024.naacl-long.182",
    pages = "3322--3345"
}