Alex Wang, Lei Pan, Raymond Lee, Saurabh Vishwas Joshi, and Chia-Wei Chen discussed the use of Ray as a last-mile data processing framework at Pinterest. They described how Ray was integrated into their ML infrastructure and how it solved critical business problems. In this post, they discussed a second type of popular application of Ray at Pinterest: offline batch inference of ML models. They also shared how their implementation was able to deliver 4.5x throughput increases and 30x cost savings.