@article{learningtoshardrlforcooptimizingtheparal,
  title = {Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference},
  author = {Ruokai Yin and Sattwik Deb Mishra and Xuan Zuo and Hokchhay Tann and Preyas Shah and Apala Guha},
  year = {2025},
  eprint = {2509.00217},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.00217},
}