@inproceedings{liang2025attnchecker,
  title={ATTNChecker: Highly-optimized fault tolerant attention for large language model training},
  author={Liang, Yuhang and Li, Xinyi and Ren, Jie and Li, Ang and Fang, Bo and Chen, Jieyang},
  booktitle={Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming},
  pages={252--266},
  year={2025}
}