concept-prebuilt-docker-images-inference.md

title	titleSuffix	description	services	ms.service	ms.subservice	ms.author	author	ms.date	ms.topic	ms.reviewer	ms.custom
Prebuilt Docker images	Azure Machine Learning	Prebuilt Docker images for inference (scoring) in Azure Machine Learning	machine-learning	machine-learning	core	ssambare	shivanissambare	10/21/2021	conceptual	larryfr	deploy, docker, prebuilt, curated environments

Prebuilt Docker images for inference

Prebuilt Docker container images for inference are used when deploying a model with Azure Machine Learning. The images are prebuilt with popular machine learning frameworks and Python packages. You can also extend the packages to add other packages by using one of the following methods:

• Add Python packages.
• Use prebuilt inference image as base for a new Dockerfile. Using this method, you can install both Python packages and apt packages.

Why should I use prebuilt images?

• Reduces model deployment latency.
• Improves model deployment success rate.
• Avoid unnecessary image build during model deployment.
• Only have required dependencies and access right in the image/container. 

List of prebuilt Docker images for inference

[!INCLUDE list-of-inference-prebuilt-docker-images]

Next steps

• Add Python packages to prebuilt images.
• Use a prebuilt package as a base for a new Dockerfile.