Add support for SageMaker Serverless Endpoint Configuration

[elwinarens]

Description

The SageMaker Endpoint Configuration feature now supports serverless endpoints by defining a ServerlessConfig on the variant:

New or Affected Resource(s)

• aws_sagemaker_endpoint_configuration

Potential Terraform Configuration

resource "aws_sagemaker_endpoint_configuration" "ec" {
  name = "my-endpoint-config"

  production_variants {
    variant_name           = "variant-1"
    model_name             = aws_sagemaker_model.m.name
 
    serverless_config {
      max_concurrency   = 10
      memory_size_in_mb = 2048
    }
  }

  tags = {
    Name = "foo"
  }
}

Suggestion to make the (provisioned) instance related configuration instance_type and initial_instance_count xor with the serverless config.

References

• https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html#API_CreateEndpointConfig_RequestSyntax
• https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/sagemaker_endpoint_configuration

[DrFaust92]

Serverless seems to be in preview and a lot of the non-serverless features are not supported at this time and subject ot change, https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints.html.

[mbragg02]

It is now generally available 🎉 https://aws.amazon.com/blogs/aws/amazon-sagemaker-serverless-inference-machine-learning-inference-without-worrying-about-servers/

[repl-jeffrey-miiller]

Any update on this?

[ronnyb2017]

We urgently need this :) Any idea by when this will get integrated ?

[janjur]

Oh come on! Guys, it's so important.

[DrFaust92]

looking into this

[github-actions]

This functionality has been released in v4.20.0 of the Terraform AWS Provider. Please see the Terraform documentation on provider versioning or reach out if you need any assistance upgrading.

For further feature requests or bug reports with this functionality, please create a new GitHub issue following the template. Thank you!

[github-actions]

I'm going to lock this issue because it has been closed for 30 days ⏳. This helps our maintainers find and focus on the active issues.
If you have found a problem that seems similar to this, please open a new issue and complete the issue template so we can capture all the details necessary to investigate further.