@article{semiclairvoyantschedulingofspeculative,
  title = {Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency},
  author = {Ruixiao Li and Fahao Chen and Peng Li},
  year = {2025},
  eprint = {2505.17074},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.17074v1},
}