@article{priorityawarepreemptiveschedulingfor,
  title = {Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference},
  author = {Mohammad Siavashi and Faezeh Keshmiri Dindarloo and Dejan Kostic and Marco Chiesa},
  year = {2025},
  eprint = {2503.09304},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.09304v1},
}