@article{250511432, title = {MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production}, author = {Chao Jin and Ziheng Jiang and Zhihao Bai and Zheng Zhong and Juncai Liu and Xiang Li and Ningxin Zheng and Xi Wang and Cong Xie and Qi Huang and Wen Heng and Yiyuan Ma and Wenlei Bao and Size Zheng and Yanghua Peng and Haibin Lin and Xuanzhe Liu and Xin Jin and Xin Liu}, year = {2025}, eprint = {2505.11432}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.11432v2}, }