InferenceComponentSchedulingConfig
¶
Source code in docs_src/capo_sagemaker/types/inference_component_scheduling_config.py
availability_zone_balance
instance-attribute
¶
availability_zone_balance: NotRequired[InferenceComponentAvailabilityZoneBalance]
Configuration for balancing inference component copies across Availability Zones.
placement_strategy
instance-attribute
¶
placement_strategy: NotRequired[InferenceComponentPlacementStrategy]
The strategy for placing inference component copies across available instances. If you also set AvailabilityZoneBalance, this strategy applies to placement within each Availability Zone.
- SPREAD
-
Distributes copies evenly across available instances for better resilience.
- BINPACK
-
Packs copies onto fewer instances to optimize resource utilization.