interface InferenceComponentRollingUpdatePolicyProperty

Language	Type name
.NET	`Amazon.CDK.AWS.Sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty`
Go	`github.com/aws/aws-cdk-go/awscdk/v2/awssagemaker#CfnInferenceComponent_InferenceComponentRollingUpdatePolicyProperty`
Java	`software.amazon.awscdk.services.sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty`
Python	`aws_cdk.aws_sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty`
TypeScript	`aws-cdk-lib` » `aws_sagemaker` » `CfnInferenceComponent` » `InferenceComponentRollingUpdatePolicyProperty`

Specifies a rolling deployment strategy for updating a SageMaker AI inference component.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';
const inferenceComponentRollingUpdatePolicyProperty: sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty = {
  maximumBatchSize: {
    type: 'type',
    value: 123,
  },
  maximumExecutionTimeoutInSeconds: 123,
  rollbackMaximumBatchSize: {
    type: 'type',
    value: 123,
  },
  waitIntervalInSeconds: 123,
};

Properties

Name	Type	Description
maximumBatchSize?	`IResolvable` `\|` `InferenceComponentCapacitySizeProperty`	The batch size for each rolling step in the deployment process.
maximumExecutionTimeoutInSeconds?	`number`	The time limit for the total deployment.
rollbackMaximumBatchSize?	`IResolvable` `\|` `InferenceComponentCapacitySizeProperty`	The batch size for a rollback to the old endpoint fleet.
waitIntervalInSeconds?	`number`	The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.

maximumBatchSize?

Type: IResolvable | InferenceComponentCapacitySizeProperty (optional)

The batch size for each rolling step in the deployment process.

For each step, SageMaker AI provisions capacity on the new endpoint fleet, routes traffic to that fleet, and terminates capacity on the old endpoint fleet. The value must be between 5% to 50% of the copy count of the inference component.

maximumExecutionTimeoutInSeconds?

Type: number (optional)

The time limit for the total deployment.

Exceeding this limit causes a timeout.

rollbackMaximumBatchSize?

Type: IResolvable | InferenceComponentCapacitySizeProperty (optional)

The batch size for a rollback to the old endpoint fleet.

If this field is absent, the value is set to the default, which is 100% of the total capacity. When the default is used, SageMaker AI provisions the entire capacity of the old fleet at once during rollback.

waitIntervalInSeconds?

Type: number (optional)

The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.