@inproceedings{cheng2023towards, title={Towards GPU Memory Efficiency for Distributed Training at Scale}, author={Cheng, Runxiang and Cai, Chris and Yilmaz, Selman and Mitra, Rahul and Bag, Malay and Ghosh, Mrinmoy and Xu, Tianyin}, booktitle={Proceedings of the 14th ACM Symposium on Cloud Computing (SoCC)}, pages={281--297}, year={2023} }