@article{efficientinferenceforaugmentedlarge,
  title = {Fast Inference for Augmented Large Language Models},
  author = {Rana Shahout and Cong Liang and Shiji Xin and Qianru Lao and Yong Cui and Minlan Yu and Michael Mitzenmacher},
  year = {2024},
  eprint = {2410.18248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.18248v2},
}