@article{cspsacommunicationefficientsequence,
  title = {PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference},
  author = {Zeyu Zhang and Haiying Shen},
  year = {2024},
  eprint = {2409.15104},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.15104v2},
}