@article{megablocksefficientsparsetrainingwith,
  title = {MegaBlocks: Efficient Sparse Training with Mixture-of-Experts},
  author = {Trevor Gale and Deepak Narayanan and Cliff Young and Matei Zaharia},
  year = {2022},
  eprint = {2211.15841},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.15841v1},
}