Vertex AI provides Docker container images that you run as pre-built containers for serving predictions and explanations from trained model artifacts. These containers, which are organized by machine learning (ML) framework and framework version, provide HTTP prediction servers that you can use to serve predictions with minimal configuration. In many cases, using a pre-built container is simpler than creating your own custom container for prediction.
This document lists the pre-built containers for predictions and explanations, and it describes how to use them with model artifacts that you created using Vertex AI's custom training functionality or model artifacts that you created outside of Vertex AI.
Available container images
Each of the following container images is available in several
Artifact Registry repositories, which store data in various
locations. You can use any of
the URIs for an image when you perform custom training; each provides the same
container image. If you use the Google Cloud console to create a Model
resource,
the Google Cloud console selects the URI that best matches the location where
you are using Vertex AI in order to reduce
latency.
TensorFlow
ML framework version | Use with GPUs? | URIs (choose any) |
---|---|---|
2.11 | No |
|
2.11 | Yes |
|
2.10 | No |
|
2.10 | Yes |
|
2.9 | No |
|
2.9 | Yes |
|
2.8 | No |
|
2.8 | Yes |
|
2.7 | No |
|
2.7 | Yes |
|
2.6 | No |
|
2.6 | Yes |
|
2.5 | No |
|
2.5 | Yes |
|
2.4 | No |
|
2.4 | Yes |
|
2.3 | No |
|
2.3 | Yes |
|
2.2 | No |
|
2.2 | Yes |
|
2.1 | No |
|
2.1 | Yes |
|
1.15 | No |
|
1.15 | Yes |
|
Optimized TensorFlow runtime (Preview)
Container images that use the optimized TensorFlow runtime are in Preview. For more information, see Use the optimized TensorFlow runtime.
ML framework version | Use with GPUs? | URIs (choose any) |
---|---|---|
nightly | No |
|
nightly | Yes |
|
2.11 | No |
|
2.11 | Yes |
|
2.10 | No |
|
2.10 | Yes |
|
2.9 | No |
|
2.9 | Yes |
|
2.8 | No |
|
2.8 | Yes |
|
scikit-learn
ML framework version | Use with GPUs? | URIs (choose any) |
---|---|---|
1.0 | No |
|
0.24 | No |
|
0.23 | No |
|
0.22 | No |
|
0.20 | No |
|
XGBoost
ML framework version | Use with GPUs? | URIs (choose any) |
---|---|---|
1.6 | No |
|
1.5 | No |
|
1.4 | No |
|
1.3 | No |
|
1.2 | No |
|
1.1 | No |
|
0.90 | No |
|
0.82 | No |
|
Use a pre-built container
You can specify a pre-built container for prediction when you
create a custom TrainingPipeline
resource that uploads a Model
or when
you import model artifacts as a Model
.