Ray Serve: Tutorial for Building Real Time Inference Pipelines

In this tutorial, we will explore how to author real-time inference pipelines in Python with Ray Serve and the deployment graph API. We will also discuss scaling and resources allocation problems and show how Ray enables you to simplify and control your deployments. This workshop is especially suited for ML-practitioners and ML-engineers who look for modern tools for scalable ML.
This talk was originally delivered at Arize:Observe 2023, a conference on the intersection of large language models, generative AI, and machine learning observability in the era of LLMops.
Learn more about Ray + Arize: arize.com/blog...
Get certified in ML observability: courses.arize.com