@article{fmoefinegrainedexpertoffloadingforlarge, title = {fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving}, author = {Hanfei Yu and Xingqi Cui and Hong Zhang and Hao Wang}, year = {2025}, eprint = {2502.05370}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.05370v1}, }