@inproceedings{singh:ics2023,
  author = {Singh, Siddharth and Ruwase, Olatunji and Awan, Ammar Ahmad and Rajbhandari, Samyam and He, Yuxiong and Bhatele, Abhinav},
  title = {A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training},
  booktitle = {Proceedings of the International Conference on Supercomputing},
  series = {ICS '23},
  year = {2023},
  month = jun,
  url = {http://doi.acm.org/10.1145/3577193.3593704}
}