@article{doescompressingactivationshelpmodel, title = {Does compressing activations help model parallel training?}, author = {Song Bian and Dacheng Li and Hongyi Wang and Eric P. Xing and Shivaram Venkataraman}, year = {2023}, eprint = {2301.02654}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2301.02654v1}, }