Package com.pulumi.aws.sagemaker.outputs

Class EndpointConfigurationProductionVariant

  • public final class EndpointConfigurationProductionVariant
extends java.lang.Object

    • Method Detail

      • acceleratorType

        public java.util.Optional<java.lang.String> acceleratorType()
        Returns:
        Size of the Elastic Inference (EI) instance to use for the production variant.

      • containerStartupHealthCheckTimeoutInSeconds

        public java.util.Optional<java.lang.Integer> containerStartupHealthCheckTimeoutInSeconds()
        Returns:
        Timeout value, in seconds, for your inference container to pass health check by SageMaker AI Hosting. For more information about health check, see [How Your Container Should Respond to Health Check (Ping) Requests](https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-algo-ping-requests). Valid values between `60` and `3600`.

      • enableSsmAccess

        public java.util.Optional<java.lang.Boolean> enableSsmAccess()
        Returns:
        Whether to turn on native AWS SSM access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind endpoints. Ignored if `modelName` is not set (Inference Components endpoint).

      • inferenceAmiVersion

        public java.util.Optional<java.lang.String> inferenceAmiVersion()
        Returns:
        Option from a collection of preconfigured AMI images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads.

      • initialInstanceCount

        public java.util.Optional<java.lang.Integer> initialInstanceCount()
        Returns:
        Initial number of instances used for auto-scaling.

      • initialVariantWeight

        public java.util.Optional<java.lang.Double> initialVariantWeight()
        Returns:
        Initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, defaults to `1.0`. Ignored if `modelName` is not set (Inference Components endpoint).

      • instanceType

        public java.util.Optional<java.lang.String> instanceType()
        Returns:
        Type of instance to start.

      • modelDataDownloadTimeoutInSeconds

        public java.util.Optional<java.lang.Integer> modelDataDownloadTimeoutInSeconds()
        Returns:
        Timeout value, in seconds, to download and extract the model that you want to host from S3 to the individual inference instance associated with this production variant. Valid values between `60` and `3600`.

      • modelName

        public java.util.Optional<java.lang.String> modelName()
        Returns:
        Name of the model to use. Required unless using Inference Components (in which case `executionRoleArn` must be specified at the endpoint configuration level).

      • variantName

        public java.util.Optional<java.lang.String> variantName()
        Returns:
        Name of the variant. If omitted, the provider will assign a random, unique name.

      • volumeSizeInGb

        public java.util.Optional<java.lang.Integer> volumeSizeInGb()
        Returns:
        Size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between `1` and `512`.