Skip to main content
Version: 1.34

Creating SageMaker Deployments

With the AWS SageMaker integration set up, you can create SageMaker Deployments. Typically, creating such a Deployment involves the steps outlined in Creating a Deployment/. However, it's worth noting that certain settings are exclusive to KServe Deployments and not applicable to SageMaker Deployments, and vice versa. In this article, we will highlight only the parts unique to SageMaker Deployments.

Prerequisities

  • You added a Repository that adheres to the requirements. Note that Repositories used for SageMaker Deployments must use the reference system.
  • (Optional) include a Blob URL and Docker reference, as illustrated in this example:
{
"reference": {
"blob": {
"url": "s3://deeploy-examples/sklearn/census/sagemaker/model.tar.gz"
},
"docker": {
"image": "492215442770.dkr.ecr.eu-central-1.amazonaws.com/sagemaker-scikit-learn:0.20.0-cpu-py3" ,
"uri": "/model:predict",
"port": 8000
}
}
}

Repository, branch and commit

Select a Repository, branch, and commit as usual.

Deployment metadata

You can change the AWS region used for the Deployment in this step.

Model framework

Only the Custom Docker model framework is allowed. Therefore, you cannot select a model framework in this step.

Click Advanced configuration to select an instance type, which gives you the flexibility to choose the appropriate mix of resources for your model. AWS offers a guide for choosing the instance type based on your use case.

Explainer Framework

Only the Custom Docker explainer framework is allowed. Therefore, can only select No explainer or Custom docker in this step.

Transformer

Transformers have been disabled for Sagemaker deployments, please include additional pre and post-processing in the model or explainer container.

Compliance

Compliance is as usual, we do assume the docker image to be on a private image registry for Sagemaker deployments.

Deploy

Click Deploy, Deeploy will now initiate the automated deployment process.