@article{universalcheckpointingefficientand, title = {Universal Checkpointing: Efficient and Flexible Checkpointing for Large Scale Distributed Training}, author = {Xinyu Lian and Sam Ade Jacobs and Lev Kurilenko and Masahiro Tanaka and Stas Bekman and Olatunji Ruwase and Minjia Zhang}, year = {2024}, eprint = {2406.18820}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.18820v2}, }