@inproceedings{chen-etal-2025-hardware,
    title = "Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of {LLM} Inference",
    author = "Chen, Hao Mark  and
      Luk, Wayne  and
      Cedric, Yiu Ka Fai  and
      Li, Rui  and
      Mishchenko, Konstantin  and
      Venieris, Stylianos  and
      Fan, Hongxiang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.120/",
    doi = "10.18653/v1/2025.findings-emnlp.120",
    pages = "2221--2238",
    ISBN = "979-8-89176-335-7"
}