@article{reasoncacheacceleratinglargereasoningmod,
  title = {ReasonCache: Accelerating Large Reasoning Model Serving through KV Cache Sharing},
  author = {Kaiwen Chen and Xin Tan and Minchen Yu and Jingzong Li and Hong Xu},
  year = {2025},
  eprint = {2507.21433},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.21433},
}