static InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.builder() |
|
default InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.maximumBatchSize(Consumer<InferenceComponentCapacitySize.Builder> maximumBatchSize) |
The batch size for each rolling step in the deployment process.
|
InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.maximumBatchSize(InferenceComponentCapacitySize maximumBatchSize) |
The batch size for each rolling step in the deployment process.
|
InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.maximumExecutionTimeoutInSeconds(Integer maximumExecutionTimeoutInSeconds) |
The time limit for the total deployment.
|
default InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.rollbackMaximumBatchSize(Consumer<InferenceComponentCapacitySize.Builder> rollbackMaximumBatchSize) |
The batch size for a rollback to the old endpoint fleet.
|
InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.rollbackMaximumBatchSize(InferenceComponentCapacitySize rollbackMaximumBatchSize) |
The batch size for a rollback to the old endpoint fleet.
|
InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.toBuilder() |
|
InferenceComponentRollingUpdatePolicy.Builder |
InferenceComponentRollingUpdatePolicy.Builder.waitIntervalInSeconds(Integer waitIntervalInSeconds) |
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
|