@article{polyrouteramultillmqueryingsystem, title = {TensorOpera Router: A Multi-Model Router for Efficient LLM Inference}, author = {Dimitris Stripelis and Zijian Hu and Jipeng Zhang and Zhaozhuo Xu and Alay Dilipbhai Shah and Han Jin and Yuhang Yao and Salman Avestimehr and Chaoyang He}, year = {2024}, eprint = {2408.12320}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.12320v3}, }