@article{250608528,
  title = {PerfTracker: Online Performance Troubleshooting for Large-scale Model Training in Production},
  author = {Yu Guan and Zhiyu Yin and Haoyu Chen and Sheng Cheng and Chaojie Yang and Kun Qian and Tianyin Xu and Yang Zhang and Hanyu Zhao and Yong Li and Wei Lin and Dennis Cai and Ennan Zhai},
  year = {2025},
  eprint = {2506.08528},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.08528v3},
}