@article{trainmoverefficientmltraininglive, title = {TrainMover: An Interruption-Resilient and Reliable ML Training Runtime}, author = {ChonLam Lao and Minlan Yu and Aditya Akella and Jiamin Cao and Yu Guan and Pengcheng Zhang and Zhilong Zheng and Yichi Xu and Ennan Zhai and Dennis Cai and Jiaqi Gao}, year = {2024}, eprint = {2412.12636}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.12636v2}, }