@misc{monteiro2024cache,
  title={XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference},
  author={João Monteiro and Étienne Marcotte and Pierre-André Noël and Valentina Zantedeschi and David Vázquez and Nicolas Chapados and Christopher Pal and Perouz Taslakian},
  year={2024},
  eprint={2404.15420},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2404.15420}
}