Specifies a rolling deployment strategy for updating a SageMaker AI inference component.
Syntax
To declare this entity in your AWS CloudFormation template, use the following syntax:
JSON
{
"MaximumBatchSize" : InferenceComponentCapacitySize,
"MaximumExecutionTimeoutInSeconds" : Integer,
"RollbackMaximumBatchSize" : InferenceComponentCapacitySize,
"WaitIntervalInSeconds" : Integer
}
YAML
MaximumBatchSize:
InferenceComponentCapacitySize
MaximumExecutionTimeoutInSeconds: Integer
RollbackMaximumBatchSize:
InferenceComponentCapacitySize
WaitIntervalInSeconds: Integer
Properties
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.
Required: No
Type: InferenceComponentCapacitySize
Update requires: No interruption
MaximumExecutionTimeoutInSeconds-
The time limit for the total deployment. Exceeding this limit causes a timeout.
Required: No
Type: Integer
Minimum:
600Maximum:
28800Update requires: No interruption
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.
Required: No
Type: InferenceComponentCapacitySize
Update requires: No interruption
WaitIntervalInSeconds-
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
Required: No
Type: Integer
Minimum:
0Maximum:
3600Update requires: No interruption
