1@article{zhang2026pretraining,
2 title={Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm},
3 author={Zhang, Jinrui icon and Xiao, Chaodong and Wu, Aoqi and Zhang, Xindong and Zhang, Lei},
4 journal={arXiv preprint arXiv:2602.11543},
5 year={2026}
6}