@article{daliaworkloadawareoffloadingframeworkfor, title = {DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs}, author = {Zeyu Zhu and Gang Li and Peisong Wang and Zitao Mo and Minnan Pei and Zhuoran Song and Xiaoyao Liang and Jian Cheng}, year = {2026}, eprint = {2602.03495}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.03495}, }