@article{antbatchinferelasticbatchinferenceinthe,
  title = {AntBatchInfer: Elastic Batch Inference in the Kubernetes Cluster},
  author = {Siyuan Li and Youshao Xiao and Fanzhuang Meng and Lin Ju and Lei Liang and Lin Wang and Jun Zhou},
  year = {2024},
  eprint = {2404.09686},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.09686v1},
}