@article{optimizinglargemodeltrainingthrough, title = {Optimizing Large Model Training through Overlapped Activation Recomputation}, author = {Ping Chen and Wenjie Zhang and Shuibing He and Weijian Chen and Siling Yang and Kexin Huang and Yanlong Yin and Xuan Zhan and Yingjie Gu and Zhuwei Peng and Yi Zheng and Zhefeng Wang and Gang Chen}, year = {2024}, eprint = {2406.08756}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.08756v4}, }