@article{expertflowoptimizedexpertactivationand,
  title = {ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference},
  author = {Xin He and Shunkang Zhang and Yuxin Wang and Haiyan Yin and Zihao Zeng and Shaohuai Shi and Zhenheng Tang and Xiaowen Chu and Ivor Tsang and Ong Yew Soon},
  year = {2024},
  eprint = {2410.17954},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.17954v1},
}