@article{onequeueisallyouneedresolvingheadof,
  title = {Queue management for slo-oriented large language model serving},
  author = {Archit Patke and Dhemath Reddy and Saurabh Jha and Haoran Qiu and Christian Pinto and Chandra Narayanaswami and Zbigniew Kalbarczyk and Ravishankar Iyer},
  year = {2024},
  eprint = {2407.00047},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.00047v2},
}