@article{dynamicstashingquantizationforefficient, title = {Dynamic Stashing Quantization for Efficient Transformer Training}, author = {Guo Yang and Daniel Lo and Robert Mullins and Yiren Zhao}, year = {2023}, eprint = {2303.05295}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2303.05295v1}, }