@misc{yi2023edgemoe, title={EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models}, author={Rongjie Yi and Liwei Guo and Shiyun Wei and Ao Zhou and Shangguang Wang and Mengwei Xu}, year={2023}, eprint={2308.14352}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2308.14352} }