报告题目：Serverless Data Science - Are We There Yet? A Case Study of Model Serving

论文出处：SIGMOD:2022 

作者：Yuncheng Wu,Tien Tuan Anh Dinh,Guoyu Hu,Meihui Zhang,Yeow Meng Chee,Beng Chin Ooi

单位：National University of Singapore，Singapore University of Technology and Design, Beijing Institute of Technology

报告人：陈张

报告时间：2022年9月19日 下午 2:00

报告地点：贵州大学北校区博学楼624室

摘要：The goal in this paper is to examine the viability of serverless as a mainstream model serving platform.The paper first conduct a comprehensive evaluation of the performance and cost of serverless against other model serving systems on Amazon Web Service and Google Cloud Platform. The paper find that serverless outperforms many cloud-based alternatives. Further, there are settings under which it even achieves better performance than GPU-based systems. Next, the paper present the design space of serverless model serving, which comprises multiple dimensions, including cloud platforms, serving runtimes, and other function-specific parameters. For each dimension, the paper analyze the impact of different choices and provide suggestions for data scientists to better utilize serverless model serving. Finally, the paper discuss challenges and opportunities in building a more practical serverless model serving system.