@inproceedings{du2024sida,
  title     = {SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models},
  author    = {Du, Zhixu and Li, Shiyu and Wu, Yuhao and Jiang, Xiangyu and Sun, Jingwei and Zheng, Qilin and Wu, Yongkai and Li, Ang and Li, Hai and Chen, Yiran},
  booktitle = {Proceedings of the Seventh Conference on Machine Learning and Systems (MLSys 2024)},
  year      = {2024},
  url       = {https://arxiv.org/abs/2310.18859}
}