@article{datacentricandheterogeneityadaptive,
  title = {FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism},
  author = {Yujie Wang and Shiju Wang and Shenhan Zhu and Fangcheng Fu and Xinyi Liu and Xuefeng Xiao and Huixia Li and Jiashi Li and Faming Wu and Bin Cui},
  year = {2024},
  eprint = {2412.01523},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.01523v3},
}