Skip to content

RealTimeInferenceConfig

Source code in docs_src/capo_sagemaker/types/real_time_inference_config.py
class RealTimeInferenceConfig(TypedDict, closed=True):
    instance_type: NotRequired[
        "capo_sagemaker.types.production_variant_instance_type.ProductionVariantInstanceType"
    ]
    """<p>The instance type the model is deployed to.</p>"""
    instance_count: NotRequired["capo_sagemaker.types.task_count.TaskCount"]
    """<p>The number of instances of the type specified by <code>InstanceType</code>.</p>"""

instance_count instance-attribute

instance_count: NotRequired[TaskCount]

The number of instances of the type specified by InstanceType.

instance_type instance-attribute

instance_type: NotRequired[ProductionVariantInstanceType]

The instance type the model is deployed to.