@article{aptserveadaptiverequestschedulingon,
  title = {Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving},
  author = {Shihong Gao and Xin Zhang and Yanyan Shen and Lei Chen},
  year = {2025},
  eprint = {2504.07494},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.07494v1},
}