@article{loongserveefficientlyservinglongcontext,
  title = {LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism},
  author = {Bingyang Wu and Shengyu Liu and Yinmin Zhong and Peng Sun and Xuanzhe Liu and Xin Jin},
  year = {2024},
  eprint = {2404.09526},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.09526v2},
}