@article{batonenhancingbatchwiseinference,
  title = {BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching},
  author = {Peizhuang Cong and Qizhi Chen and Haochen Zhao and Tong Yang},
  year = {2024},
  eprint = {2410.18701},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.18701v1},
}