sagemaker: Support retention of variant properties for endpoints

[petermeansrock]

Describe the feature

As described in the SageMaker Endpoint L2 construct RFC:

Retention of Variant Properties: Once an endpoint has been deployed, the desired instance count and desired weight can be dynamically adjusted per production variant without changing the backing endpoint config resource. These changes can either be made automatically via Application Auto Scaling or manually by the customer via the SageMaker UpdateEndpointWeightsAndCapacities operation. After making such changes, by default, when updating a SageMaker endpoint to use a new endpoint config resource (such as when making a CloudFormation change an endpoint config that results in resource replacement), the desired instance count and desired weight is reset to match the new endpoint config resource. To bypass this resetting of variant properties, the RetainAllVariantProperties boolean flag was added to the endpoint resource, which when set to true, will not reset these variant properties. In addition to this field, ExcludeRetainedVariantProperties was also added to the endpoint resource to allow for selective retention of variant properties (e.g., keeping the desired instance count while resetting the desired weight).

Please 👍 this issue to help with the prioritization of this feature.

Use Case

Changes made to a deployed endpoint's variants' properties (e.g., desired instance count, desired weight), either automatically via Application Auto Scaling or manually by the customer via the SageMaker UpdateEndpointWeightsAndCapacities operation, should conditionally be retained during CloudFormation stack updates to prevent artificial resetting of endpoint state (e.g., scaling down an auto-scaled fleet, shifting traffic away from a manually adjusted set of weights).

Proposed Solution

As described in the SageMaker Endpoint L2 construct RFC:

As the default behavior is already in place (no retention), adding the functionality should consist of incorporating new attribute(s) on the Endpoint L2 construct's props interface and plumbing it through to the underlying L1 resource definition.

Other Information

No response

Acknowledgements

• I may be able to implement this feature request
• This feature might incur a breaking change

CDK version used

2.54.0-alpha.0

Environment details (OS name and version, etc.)

macOS Ventura