@article{aschedulingframeworkforefficientmoeinfer, title = {A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems}, author = {Qi Wu and Chao Fang and Jiayuan Chen and Ye Lin and Yueqi Zhang and Yichuan Bai and Yuan Du and Li Du}, year = {2026}, eprint = {2601.03992}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.03992}, }