SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines.

@inproceedings{cheng-2025-scoot, author = {Ke Cheng and Zhi Wang and Wen Hu and Tiannuo Yang and Jianguo Li and Sheng Zhang}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {829--839}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714930}, doi = {https://doi.org/10.1145/3696410.3714930} }