@misc{wang2024towards,
  title={Towards Efficient and Reliable LLM Serving: A Real-World Workload Study},
  author={Yuxin Wang and Yuhan Chen and Zeyu Li and Zhenheng Tang and Rui Guo and Xin Wang and Qiang Wang and Amelie Chi Zhou and Xiaowen Chu},
  year={2024},
  eprint={2401.17644},
  archivePrefix={arXiv},
  primaryClass={cs.DC},
  url={https://arxiv.org/abs/2401.17644}
}