/AWS1/CL_SGMINFERENCECOMPONE10¶
Specifies a rolling deployment strategy for updating a SageMaker AI inference component.
CONSTRUCTOR¶
IMPORTING¶
Required arguments:¶
io_maximumbatchsize TYPE REF TO /AWS1/CL_SGMINFERENCECOMPONE11 /AWS1/CL_SGMINFERENCECOMPONE11¶
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.
iv_waitintervalinseconds TYPE /AWS1/SGMWAITINTERVALINSECONDS /AWS1/SGMWAITINTERVALINSECONDS¶
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
Optional arguments:¶
iv_maxexectimeoutinseconds TYPE /AWS1/SGMMAXEXECTMOUTINSECONDS /AWS1/SGMMAXEXECTMOUTINSECONDS¶
The time limit for the total deployment. Exceeding this limit causes a timeout.
io_rollbackmaximumbatchsize TYPE REF TO /AWS1/CL_SGMINFERENCECOMPONE11 /AWS1/CL_SGMINFERENCECOMPONE11¶
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.
Queryable Attributes¶
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_MAXIMUMBATCHSIZE() |
Getter for MAXIMUMBATCHSIZE |
WaitIntervalInSeconds¶
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_WAITINTERVALINSECONDS() |
Getter for WAITINTERVALINSECONDS, with configurable default |
ASK_WAITINTERVALINSECONDS() |
Getter for WAITINTERVALINSECONDS w/ exceptions if field has |
HAS_WAITINTERVALINSECONDS() |
Determine if WAITINTERVALINSECONDS has a value |
MaximumExecutionTimeoutInSeconds¶
The time limit for the total deployment. Exceeding this limit causes a timeout.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_MAXEXECTIMEOUTINSECONDS() |
Getter for MAXIMUMEXECTIMEOUTINSECONDS, with configurable de |
ASK_MAXEXECTIMEOUTINSECONDS() |
Getter for MAXIMUMEXECTIMEOUTINSECONDS w/ exceptions if fiel |
HAS_MAXEXECTIMEOUTINSECONDS() |
Determine if MAXIMUMEXECTIMEOUTINSECONDS has a value |
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.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_ROLLBACKMAXIMUMBATCHSIZE() |
Getter for ROLLBACKMAXIMUMBATCHSIZE |