Interface InferenceComponentRollingUpdatePolicy.Builder

All Superinterfaces:
Buildable, CopyableBuilder<InferenceComponentRollingUpdatePolicy.Builder,InferenceComponentRollingUpdatePolicy>, SdkBuilder<InferenceComponentRollingUpdatePolicy.Builder,InferenceComponentRollingUpdatePolicy>, SdkPojo
Enclosing class:
InferenceComponentRollingUpdatePolicy
@Mutable @NotThreadSafe public static interface InferenceComponentRollingUpdatePolicy.Builder extends SdkPojo, CopyableBuilder<InferenceComponentRollingUpdatePolicy.Builder,InferenceComponentRollingUpdatePolicy>

  • Method Details

    • maximumBatchSize

      InferenceComponentRollingUpdatePolicy.Builder maximumBatchSize(InferenceComponentCapacitySize maximumBatchSize)

      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.

      Parameters:
      maximumBatchSize - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • maximumBatchSize

      default InferenceComponentRollingUpdatePolicy.Builder maximumBatchSize(Consumer<InferenceComponentCapacitySize.Builder> maximumBatchSize)

      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.

      This is a convenience method that creates an instance of the InferenceComponentCapacitySize.Builder avoiding the need to create one manually via InferenceComponentCapacitySize.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to maximumBatchSize(InferenceComponentCapacitySize).

      Parameters:
      maximumBatchSize - a consumer that will call methods on InferenceComponentCapacitySize.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • waitIntervalInSeconds

      InferenceComponentRollingUpdatePolicy.Builder waitIntervalInSeconds(Integer waitIntervalInSeconds)

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

      Parameters:
      waitIntervalInSeconds - The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • maximumExecutionTimeoutInSeconds

      InferenceComponentRollingUpdatePolicy.Builder maximumExecutionTimeoutInSeconds(Integer maximumExecutionTimeoutInSeconds)

      The time limit for the total deployment. Exceeding this limit causes a timeout.

      Parameters:
      maximumExecutionTimeoutInSeconds - The time limit for the total deployment. Exceeding this limit causes a timeout.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • rollbackMaximumBatchSize

      InferenceComponentRollingUpdatePolicy.Builder rollbackMaximumBatchSize(InferenceComponentCapacitySize rollbackMaximumBatchSize)

      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.

      Parameters:
      rollbackMaximumBatchSize - 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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • rollbackMaximumBatchSize

      default InferenceComponentRollingUpdatePolicy.Builder rollbackMaximumBatchSize(Consumer<InferenceComponentCapacitySize.Builder> rollbackMaximumBatchSize)

      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.

      This is a convenience method that creates an instance of the InferenceComponentCapacitySize.Builder avoiding the need to create one manually via InferenceComponentCapacitySize.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to rollbackMaximumBatchSize(InferenceComponentCapacitySize).

      Parameters:
      rollbackMaximumBatchSize - a consumer that will call methods on InferenceComponentCapacitySize.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also: