Class: Aws::SageMaker::Types::InferenceComponentRollingUpdatePolicy
- Inherits:
-
Struct
- Object
- Struct
- Aws::SageMaker::Types::InferenceComponentRollingUpdatePolicy
- Includes:
- Aws::Structure
- Defined in:
- lib/aws-sdk-sagemaker/types.rb
Overview
Specifies a rolling deployment strategy for updating a SageMaker AI inference component.
Constant Summary collapse
- SENSITIVE =
[]
Instance Attribute Summary collapse
-
#maximum_batch_size ⇒ Types::InferenceComponentCapacitySize
The batch size for each rolling step in the deployment process.
-
#maximum_execution_timeout_in_seconds ⇒ Integer
The time limit for the total deployment.
-
#rollback_maximum_batch_size ⇒ Types::InferenceComponentCapacitySize
The batch size for a rollback to the old endpoint fleet.
-
#wait_interval_in_seconds ⇒ Integer
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
Instance Attribute Details
#maximum_batch_size ⇒ Types::InferenceComponentCapacitySize
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.
25633 25634 25635 25636 25637 25638 25639 25640 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 25633 class InferenceComponentRollingUpdatePolicy < Struct.new( :maximum_batch_size, :wait_interval_in_seconds, :maximum_execution_timeout_in_seconds, :rollback_maximum_batch_size) SENSITIVE = [] include Aws::Structure end |
#maximum_execution_timeout_in_seconds ⇒ Integer
The time limit for the total deployment. Exceeding this limit causes a timeout.
25633 25634 25635 25636 25637 25638 25639 25640 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 25633 class InferenceComponentRollingUpdatePolicy < Struct.new( :maximum_batch_size, :wait_interval_in_seconds, :maximum_execution_timeout_in_seconds, :rollback_maximum_batch_size) SENSITIVE = [] include Aws::Structure end |
#rollback_maximum_batch_size ⇒ Types::InferenceComponentCapacitySize
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.
25633 25634 25635 25636 25637 25638 25639 25640 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 25633 class InferenceComponentRollingUpdatePolicy < Struct.new( :maximum_batch_size, :wait_interval_in_seconds, :maximum_execution_timeout_in_seconds, :rollback_maximum_batch_size) SENSITIVE = [] include Aws::Structure end |
#wait_interval_in_seconds ⇒ Integer
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
25633 25634 25635 25636 25637 25638 25639 25640 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 25633 class InferenceComponentRollingUpdatePolicy < Struct.new( :maximum_batch_size, :wait_interval_in_seconds, :maximum_execution_timeout_in_seconds, :rollback_maximum_batch_size) SENSITIVE = [] include Aws::Structure end |