@article{pretrainingalargelanguagemodelusingdistr,
  title = {Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm},
  author = {Jinrui Zhang and Chaodong Xiao and Aoqi Wu and Xindong Zhang and Lei Zhang},
  year = {2026},
  eprint = {2602.11543},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.11543},
}