@misc{indiciae3aa8fddefdb5,
  title = {An Efficient Checkpointing System for Large Machine Learning Model Training},
  author = {Xu, Wubiao and Huang, Xin and Meng, Shiman and Zhang, Weiping and Guo, Luanzheng and Sato, Kento},
  year = {2024},
  doi = {10.1109/scw63240.2024.00127},
  url = {https://www.osti.gov/biblio/2526231},
  note = {Source identifier: 2526231}
}