@article{lightseqacceleratedtrainingfortransforme, title = {LightSeq2: Accelerated Training for Transformer-based Models on GPUs}, author = {Xiaohui Wang and Yang Wei and Ying Xiong and Guyue Huang and Xian Qian and Yufei Ding and Mingxuan Wang and Lei LI}, year = {2021}, eprint = {2110.05722}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2110.05722v3}, }