RealTimeInferenceConfig
¶
Source code in docs_src/capo_sagemaker/types/real_time_inference_config.py
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.