@inproceedings{potamitis-etal-2025-cache,
    title = "Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible {LLM} Inference",
    author = "Potamitis, Nearchos  and
      Klein, Lars Henning  and
      Mohammadi, Bardia  and
      Xu, Chongyang  and
      Mukherjee, Attreyee  and
      Tandon, Niket  and
      Bindschaedler, Laurent  and
      Arora, Akhil",
    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.1402/",
    doi = "10.18653/v1/2025.findings-emnlp.1402",
    pages = "25703--25724",
    ISBN = "979-8-89176-335-7"
}