@article{tinyservequeryawarecacheselectionforeffi,
  title = {TinyServe: Query-Aware Cache Selection for Efficient LLM Serving},
  author = {Dong Liu and Yanxuan Yu},
  year = {2025},
  eprint = {2509.12211},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.12211},
}