@inproceedings{stripelis-etal-2024-tensoropera,
    title = "{T}ensor{O}pera Router: A Multi-Model Router for Efficient {LLM} Inference",
    author = "Stripelis, Dimitris  and
      Xu, Zhaozhuo  and
      Hu, Zijian  and
      Shah, Alay Dilipbhai  and
      Jin, Han  and
      Yao, Yuhang  and
      Zhang, Jipeng  and
      Zhang, Tong  and
      Avestimehr, Salman  and
      He, Chaoyang",
    editor = "Dernoncourt, Franck  and
      Preo{\c{t}}iuc-Pietro, Daniel  and
      Shimorina, Anastasia",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-industry.34/",
    doi = "10.18653/v1/2024.emnlp-industry.34",
    pages = "452--462",
    abstract = "With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present TO-Router, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query`s requirements. Through extensive experiments, we demonstrate that when compared to standalone expert models, TO-Router improves query efficiency by up to 40{\%}, and leads to significant cost reductions of up to 30{\%}, while maintaining or enhancing model performance by up to 10{\%}."
}