Package com.pulumi.aws.sagemaker.inputs

Class EndpointConfigurationProductionVariantArgs.Builder

    • Method Detail

      • acceleratorType

        public EndpointConfigurationProductionVariantArgs.Builder acceleratorType​(@Nullable
                                                                          com.pulumi.core.Output<java.lang.String> acceleratorType)
        Parameters:
        acceleratorType - Size of the Elastic Inference (EI) instance to use for the production variant.
        Returns:
        builder

      • acceleratorType

        public EndpointConfigurationProductionVariantArgs.Builder acceleratorType​(java.lang.String acceleratorType)
        Parameters:
        acceleratorType - Size of the Elastic Inference (EI) instance to use for the production variant.
        Returns:
        builder

      • containerStartupHealthCheckTimeoutInSeconds

        public EndpointConfigurationProductionVariantArgs.Builder containerStartupHealthCheckTimeoutInSeconds​(@Nullable
                                                                                                      com.pulumi.core.Output<java.lang.Integer> containerStartupHealthCheckTimeoutInSeconds)
        Parameters:
        containerStartupHealthCheckTimeoutInSeconds - 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`.
        Returns:
        builder

      • containerStartupHealthCheckTimeoutInSeconds

        public EndpointConfigurationProductionVariantArgs.Builder containerStartupHealthCheckTimeoutInSeconds​(java.lang.Integer containerStartupHealthCheckTimeoutInSeconds)
        Parameters:
        containerStartupHealthCheckTimeoutInSeconds - 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`.
        Returns:
        builder

      • enableSsmAccess

        public EndpointConfigurationProductionVariantArgs.Builder enableSsmAccess​(@Nullable
                                                                          com.pulumi.core.Output<java.lang.Boolean> enableSsmAccess)
        Parameters:
        enableSsmAccess - 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).
        Returns:
        builder

      • enableSsmAccess

        public EndpointConfigurationProductionVariantArgs.Builder enableSsmAccess​(java.lang.Boolean enableSsmAccess)
        Parameters:
        enableSsmAccess - 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).
        Returns:
        builder

      • inferenceAmiVersion

        public EndpointConfigurationProductionVariantArgs.Builder inferenceAmiVersion​(@Nullable
                                                                              com.pulumi.core.Output<java.lang.String> inferenceAmiVersion)
        Parameters:
        inferenceAmiVersion - 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.
        Returns:
        builder

      • inferenceAmiVersion

        public EndpointConfigurationProductionVariantArgs.Builder inferenceAmiVersion​(java.lang.String inferenceAmiVersion)
        Parameters:
        inferenceAmiVersion - 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.
        Returns:
        builder

      • initialInstanceCount

        public EndpointConfigurationProductionVariantArgs.Builder initialInstanceCount​(@Nullable
                                                                               com.pulumi.core.Output<java.lang.Integer> initialInstanceCount)
        Parameters:
        initialInstanceCount - Initial number of instances used for auto-scaling.
        Returns:
        builder

      • initialInstanceCount

        public EndpointConfigurationProductionVariantArgs.Builder initialInstanceCount​(java.lang.Integer initialInstanceCount)
        Parameters:
        initialInstanceCount - Initial number of instances used for auto-scaling.
        Returns:
        builder

      • initialVariantWeight

        public EndpointConfigurationProductionVariantArgs.Builder initialVariantWeight​(@Nullable
                                                                               com.pulumi.core.Output<java.lang.Double> initialVariantWeight)
        Parameters:
        initialVariantWeight - 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).
        Returns:
        builder

      • initialVariantWeight

        public EndpointConfigurationProductionVariantArgs.Builder initialVariantWeight​(java.lang.Double initialVariantWeight)
        Parameters:
        initialVariantWeight - 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).
        Returns:
        builder

      • modelDataDownloadTimeoutInSeconds

        public EndpointConfigurationProductionVariantArgs.Builder modelDataDownloadTimeoutInSeconds​(@Nullable
                                                                                            com.pulumi.core.Output<java.lang.Integer> modelDataDownloadTimeoutInSeconds)
        Parameters:
        modelDataDownloadTimeoutInSeconds - 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`.
        Returns:
        builder

      • modelDataDownloadTimeoutInSeconds

        public EndpointConfigurationProductionVariantArgs.Builder modelDataDownloadTimeoutInSeconds​(java.lang.Integer modelDataDownloadTimeoutInSeconds)
        Parameters:
        modelDataDownloadTimeoutInSeconds - 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`.
        Returns:
        builder

      • modelName

        public EndpointConfigurationProductionVariantArgs.Builder modelName​(@Nullable
                                                                    com.pulumi.core.Output<java.lang.String> modelName)
        Parameters:
        modelName - Name of the model to use. Required unless using Inference Components (in which case `executionRoleArn` must be specified at the endpoint configuration level).
        Returns:
        builder

      • modelName

        public EndpointConfigurationProductionVariantArgs.Builder modelName​(java.lang.String modelName)
        Parameters:
        modelName - Name of the model to use. Required unless using Inference Components (in which case `executionRoleArn` must be specified at the endpoint configuration level).
        Returns:
        builder

      • variantName

        public EndpointConfigurationProductionVariantArgs.Builder variantName​(@Nullable
                                                                      com.pulumi.core.Output<java.lang.String> variantName)
        Parameters:
        variantName - Name of the variant. If omitted, the provider will assign a random, unique name.
        Returns:
        builder

      • volumeSizeInGb

        public EndpointConfigurationProductionVariantArgs.Builder volumeSizeInGb​(@Nullable
                                                                         com.pulumi.core.Output<java.lang.Integer> volumeSizeInGb)
        Parameters:
        volumeSizeInGb - Size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between `1` and `512`.
        Returns:
        builder

      • volumeSizeInGb

        public EndpointConfigurationProductionVariantArgs.Builder volumeSizeInGb​(java.lang.Integer volumeSizeInGb)
        Parameters:
        volumeSizeInGb - Size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between `1` and `512`.
        Returns:
        builder