Skip to main content
Version: Latest


Check your docs version

These docs are for the new Anyscale design. If you started using Anyscale before April 2024, use Version 1.0.0 of the docs. If you're transitioning to Anyscale Preview, see the guide for how to migrate.

Deploy your machine learning applications in production using Ray Serve, an open-source, distributed serving library for building online inference APIs.

Anyscale Services are a production-ready way to deploy Ray Serve applications, including key stability and performance features:

  • Fault tolerance: handle replica- and node-level failures without interruptions.

  • Zero downtime updates: safely update your applications using production-ready rollouts.

  • Autoscaling: use only the compute you need by dynamically adding and removing replicas in response to traffic.

  • Monitoring and observability: monitor service health and debug issues with an integrated UI, including log search, and metrics dashboards for key performance indicators.

Get started

  1. Sign in or sign up for an account.
  2. Select the Intro to Services example.
  3. Select Launch.
  4. Follow the notebook or view it in the docs.
  5. Terminate the workspace when you're done.

Intro to Services