@article{shortcutconnectedexpertparallelismfor, title = {Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts}, author = {Weilin Cai and Juyong Jiang and Le Qin and Junwei Cui and Sunghun Kim and Jiayi Huang}, year = {2024}, eprint = {2404.05019}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.05019v3}, }