@article{symphonyoptimizedmodelservingusing, title = {Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling}, author = {Lequn Chen and Weixin Deng and Anirudh Canumalla and Yu Xin and Danyang Zhuo and Matthai Philipose and Arvind Krishnamurthy}, year = {2023}, eprint = {2308.07470}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.07470v2}, }