@article{cheng2024scoot,<br>
    &nbsp;&nbsp;&nbsp;&nbsp; title={Towards SLO-Optimized LLM Serving via Automatic Inference Engine Tuning},<br>
    &nbsp;&nbsp;&nbsp;&nbsp; author={Ke, Cheng and Zhi, Wang and Wen, Hu and Tiannuo, Yang and Jianguo, Li and Sheng, Zhang},<br>
    &nbsp;&nbsp;&nbsp;&nbsp; journal={arXiv preprint arXiv:2408.04323},<br>
    &nbsp;&nbsp;&nbsp;&nbsp; year={2024}<br>
  }