@article{efficientinteractivellmservingwithproxy,
  title = {Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction},
  author = {Haoran Qiu and Weichao Mao and Archit Patke and Shengkun Cui and Saurabh Jha and Chen Wang and Hubertus Franke and Zbigniew T. Kalbarczyk and Tamer Başar and Ravishankar K. Iyer},
  year = {2024},
  eprint = {2404.08509},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.08509v2},
}