@article{zeromemoryoptimizationtowardstraininga, title = {ZeRO: Memory Optimizations Toward Training Trillion Parameter Models}, author = {Samyam Rajbhandari and Jeff Rasley and Olatunji Ruwase and Yuxiong He}, year = {2019}, eprint = {1910.02054}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1910.02054v3}, }