@article{hetermoeefficienttrainingofmixtureof, title = {HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs}, author = {Yongji Wu and Xueshen Liu and Shuowei Jin and Ceyu Xu and Feng Qian and Z. Morley Mao and Matthew Lentz and Danyang Zhuo and Ion Stoica}, year = {2025}, eprint = {2504.03871}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.03871v1}, }