@article{oobleckresilientdistributedtrainingof, title = {Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates}, author = {Insu Jang and Zhenning Yang and Zhen Zhang and Xin Jin and Mosharaf Chowdhury}, year = {2023}, eprint = {2309.08125}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2309.08125v2}, }