@article{promoefastmoebasedllmservingusing,
  title = {ProMoE: Fast MoE-based LLM Serving using Proactive Caching},
  author = {Xiaoniu Song and Zihang Zhong and Rong Chen and Haibo Chen},
  year = {2024},
  eprint = {2410.22134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.22134v2},
}