@inproceedings{qiao-etal-2025-swiftkv,
    title = "{S}wift{KV}: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation",
    author = "Qiao, Aurick  and
      Yao, Zhewei  and
      Rajbhandari, Samyam  and
      He, Yuxiong",
    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.1306/",
    pages = "25745--25764",
    ISBN = "979-8-89176-332-6"
}