@article{deamoeefficientmoestructureforfastsmallb, title = {DeaMoE: Efficient MoE Structure for Fast Small-Batch Decoding}, author = {Zewen Jin and Shen Fu and Zeping Duan and Shannon Wang and Weihao Wu and Chengjie Tang and Congkun Ai and Ping Gong and Zijian Dai and Youhui Bai and Cheng Li}, year = {2026}, eprint = {2608.14385}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.14385}, }