@article{conveyorefficienttoolawarellmserving,
  title = {Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution},
  author = {Yechen Xu and Xinhao Kong and Tingjun Chen and Danyang Zhuo},
  year = {2024},
  eprint = {2406.00059},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.00059v2},
}