@article{servingmoemodelsonresourceconstrained,
  title = {SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget},
  author = {Rui Kong and Yuanchun Li and Qingtian Feng and Weijun Wang and Xiaozhou Ye and Ye Ouyang and Linghe Kong and Yunxin Liu},
  year = {2023},
  eprint = {2308.15030},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.15030v4},
}