InferenceComponentSpecificationSummary ¶

class InferenceComponentSpecificationSummary(TypedDict, closed=True):
    instance_type: NotRequired[
        "capo_sagemaker.types.production_variant_instance_type.ProductionVariantInstanceType"
    ]
    """<p>The ML compute instance type associated with this inference component specification.</p>"""
    model_name: NotRequired["capo_sagemaker.types.model_name.ModelName"]
    """<p>The name of the SageMaker AI model object that is deployed with the inference component.</p>"""
    container: NotRequired[
        "capo_sagemaker.types.inference_component_container_specification_summary.InferenceComponentContainerSpecificationSummary"
    ]
    """<p>Details about the container that provides the runtime environment for the model that is deployed with the inference component.</p>"""
    startup_parameters: NotRequired[
        "capo_sagemaker.types.inference_component_startup_parameters.InferenceComponentStartupParameters"
    ]
    """<p>Settings that take effect while the model container starts up.</p>"""
    compute_resource_requirements: NotRequired[
        "capo_sagemaker.types.inference_component_compute_resource_requirements.InferenceComponentComputeResourceRequirements"
    ]
    """<p>The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.</p>"""
    base_inference_component_name: NotRequired[
        "capo_sagemaker.types.inference_component_name.InferenceComponentName"
    ]
    """<p>The name of the base inference component that contains this inference component.</p>"""
    data_cache_config: NotRequired[
        "capo_sagemaker.types.inference_component_data_cache_config_summary.InferenceComponentDataCacheConfigSummary"
    ]
    """<p>Settings that affect how the inference component caches data.</p>"""
    scheduling_config: NotRequired[
        "capo_sagemaker.types.inference_component_scheduling_config.InferenceComponentSchedulingConfig"
    ]
    """<p>The scheduling configuration that determines how inference component copies are placed across available instances when copies are added or removed.</p>"""