@article{mesaamemorysavingtrainingframeworkfor, title = {Mesa: A Memory-saving Training Framework for Transformers}, author = {Zizheng Pan and Peng Chen and Haoyu He and Jing Liu and Jianfei Cai and Bohan Zhuang}, year = {2021}, eprint = {2111.11124}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2111.11124v3}, }