Skip to content

InferenceComponentSchedulingConfig

Source code in docs_src/capo_sagemaker/types/inference_component_scheduling_config.py
class InferenceComponentSchedulingConfig(TypedDict, closed=True):
    placement_strategy: NotRequired[
        "capo_sagemaker.types.inference_component_placement_strategy.InferenceComponentPlacementStrategy"
    ]
    """<p>The strategy for placing inference component copies across available instances. If you also set <code>AvailabilityZoneBalance</code>, this strategy applies to placement within each Availability Zone.</p> <dl> <dt>SPREAD</dt> <dd> <p>Distributes copies evenly across available instances for better resilience.</p> </dd> <dt>BINPACK</dt> <dd> <p>Packs copies onto fewer instances to optimize resource utilization.</p> </dd> </dl>"""
    availability_zone_balance: NotRequired[
        "capo_sagemaker.types.inference_component_availability_zone_balance.InferenceComponentAvailabilityZoneBalance"
    ]
    """<p>Configuration for balancing inference component copies across Availability Zones.</p>"""

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.