@article{cacherouteplannedprefixaffinityroutingfo,
  title = {CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM Serving},
  author = {Huang Cheng},
  year = {2026},
  eprint = {2608.19677},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.19677},
}