@article{pregatedmoeanalgorithmsystemcodesign,
  title = {Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference},
  author = {Ranggi Hwang and Jianyu Wei and Shijie Cao and Changho Hwang and Xiaohu Tang and Ting Cao and Mao Yang},
  year = {2023},
  eprint = {2308.12066},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.12066v3},
}