@article{pagedattentionmeetsflexattentionunlockin,
  title = {Paged Attention Meets FlexAttention: Unlocking Long-Context Efficiency in Deployed Inference},
  author = {Thomas Joshi and Herman Saini and Neil Dhillon and Antoni Viros i Martin and Kaoutar El Maghraoui},
  year = {2025},
  eprint = {2506.07311},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.07311v1},
}