aws logo
AWS Classic v5.33.0, Mar 24 23

aws.sagemaker.EndpointConfiguration

Provides a SageMaker endpoint configuration resource.

Example Usage

Basic usage

using System.Collections.Generic;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var ec = new Aws.Sagemaker.EndpointConfiguration("ec", new()
    {
        ProductionVariants = new[]
        {
            new Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantArgs
            {
                VariantName = "variant-1",
                ModelName = aws_sagemaker_model.M.Name,
                InitialInstanceCount = 1,
                InstanceType = "ml.t2.medium",
            },
        },
        Tags = 
        {
            { "Name", "foo" },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewEndpointConfiguration(ctx, "ec", &sagemaker.EndpointConfigurationArgs{
			ProductionVariants: sagemaker.EndpointConfigurationProductionVariantArray{
				&sagemaker.EndpointConfigurationProductionVariantArgs{
					VariantName:          pulumi.String("variant-1"),
					ModelName:            pulumi.Any(aws_sagemaker_model.M.Name),
					InitialInstanceCount: pulumi.Int(1),
					InstanceType:         pulumi.String("ml.t2.medium"),
				},
			},
			Tags: pulumi.StringMap{
				"Name": pulumi.String("foo"),
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}
package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.EndpointConfiguration;
import com.pulumi.aws.sagemaker.EndpointConfigurationArgs;
import com.pulumi.aws.sagemaker.inputs.EndpointConfigurationProductionVariantArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var ec = new EndpointConfiguration("ec", EndpointConfigurationArgs.builder()        
            .productionVariants(EndpointConfigurationProductionVariantArgs.builder()
                .variantName("variant-1")
                .modelName(aws_sagemaker_model.m().name())
                .initialInstanceCount(1)
                .instanceType("ml.t2.medium")
                .build())
            .tags(Map.of("Name", "foo"))
            .build());

    }
}
import pulumi
import pulumi_aws as aws

ec = aws.sagemaker.EndpointConfiguration("ec",
    production_variants=[aws.sagemaker.EndpointConfigurationProductionVariantArgs(
        variant_name="variant-1",
        model_name=aws_sagemaker_model["m"]["name"],
        initial_instance_count=1,
        instance_type="ml.t2.medium",
    )],
    tags={
        "Name": "foo",
    })
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const ec = new aws.sagemaker.EndpointConfiguration("ec", {
    productionVariants: [{
        variantName: "variant-1",
        modelName: aws_sagemaker_model.m.name,
        initialInstanceCount: 1,
        instanceType: "ml.t2.medium",
    }],
    tags: {
        Name: "foo",
    },
});
resources:
  ec:
    type: aws:sagemaker:EndpointConfiguration
    properties:
      productionVariants:
        - variantName: variant-1
          modelName: ${aws_sagemaker_model.m.name}
          initialInstanceCount: 1
          instanceType: ml.t2.medium
      tags:
        Name: foo

Create EndpointConfiguration Resource

new EndpointConfiguration(name: string, args: EndpointConfigurationArgs, opts?: CustomResourceOptions);
@overload
def EndpointConfiguration(resource_name: str,
                          opts: Optional[ResourceOptions] = None,
                          async_inference_config: Optional[EndpointConfigurationAsyncInferenceConfigArgs] = None,
                          data_capture_config: Optional[EndpointConfigurationDataCaptureConfigArgs] = None,
                          kms_key_arn: Optional[str] = None,
                          name: Optional[str] = None,
                          production_variants: Optional[Sequence[EndpointConfigurationProductionVariantArgs]] = None,
                          shadow_production_variants: Optional[Sequence[EndpointConfigurationShadowProductionVariantArgs]] = None,
                          tags: Optional[Mapping[str, str]] = None)
@overload
def EndpointConfiguration(resource_name: str,
                          args: EndpointConfigurationArgs,
                          opts: Optional[ResourceOptions] = None)
func NewEndpointConfiguration(ctx *Context, name string, args EndpointConfigurationArgs, opts ...ResourceOption) (*EndpointConfiguration, error)
public EndpointConfiguration(string name, EndpointConfigurationArgs args, CustomResourceOptions? opts = null)
public EndpointConfiguration(String name, EndpointConfigurationArgs args)
public EndpointConfiguration(String name, EndpointConfigurationArgs args, CustomResourceOptions options)
type: aws:sagemaker:EndpointConfiguration
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

name string
The unique name of the resource.
args EndpointConfigurationArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name str
The unique name of the resource.
args EndpointConfigurationArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name string
The unique name of the resource.
args EndpointConfigurationArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name string
The unique name of the resource.
args EndpointConfigurationArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name String
The unique name of the resource.
args EndpointConfigurationArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

EndpointConfiguration Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

The EndpointConfiguration resource accepts the following input properties:

ProductionVariants List<Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantArgs>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

AsyncInferenceConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

DataCaptureConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

KmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

Name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

ShadowProductionVariants List<Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationShadowProductionVariantArgs>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

Tags Dictionary<string, string>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

ProductionVariants []EndpointConfigurationProductionVariantArgs

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

AsyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

DataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

KmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

Name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

ShadowProductionVariants []EndpointConfigurationShadowProductionVariantArgs

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

Tags map[string]string

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

productionVariants List<EndpointConfigurationProductionVariantArgs>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

asyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name String

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

shadowProductionVariants List<EndpointConfigurationShadowProductionVariantArgs>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Map<String,String>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

productionVariants EndpointConfigurationProductionVariantArgs[]

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

asyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

shadowProductionVariants EndpointConfigurationShadowProductionVariantArgs[]

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags {[key: string]: string}

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

production_variants Sequence[EndpointConfigurationProductionVariantArgs]

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

async_inference_config EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

data_capture_config EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kms_key_arn str

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name str

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

shadow_production_variants Sequence[EndpointConfigurationShadowProductionVariantArgs]

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Mapping[str, str]

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

productionVariants List<Property Map>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

asyncInferenceConfig Property Map

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig Property Map

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name String

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

shadowProductionVariants List<Property Map>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Map<String>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

Outputs

All input properties are implicitly available as output properties. Additionally, the EndpointConfiguration resource produces the following output properties:

Arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

Id string

The provider-assigned unique ID for this managed resource.

TagsAll Dictionary<string, string>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

Id string

The provider-assigned unique ID for this managed resource.

TagsAll map[string]string

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn String

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

id String

The provider-assigned unique ID for this managed resource.

tagsAll Map<String,String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

id string

The provider-assigned unique ID for this managed resource.

tagsAll {[key: string]: string}

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn str

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

id str

The provider-assigned unique ID for this managed resource.

tags_all Mapping[str, str]

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn String

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

id String

The provider-assigned unique ID for this managed resource.

tagsAll Map<String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Look up Existing EndpointConfiguration Resource

Get an existing EndpointConfiguration resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: EndpointConfigurationState, opts?: CustomResourceOptions): EndpointConfiguration
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        async_inference_config: Optional[EndpointConfigurationAsyncInferenceConfigArgs] = None,
        data_capture_config: Optional[EndpointConfigurationDataCaptureConfigArgs] = None,
        kms_key_arn: Optional[str] = None,
        name: Optional[str] = None,
        production_variants: Optional[Sequence[EndpointConfigurationProductionVariantArgs]] = None,
        shadow_production_variants: Optional[Sequence[EndpointConfigurationShadowProductionVariantArgs]] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None) -> EndpointConfiguration
func GetEndpointConfiguration(ctx *Context, name string, id IDInput, state *EndpointConfigurationState, opts ...ResourceOption) (*EndpointConfiguration, error)
public static EndpointConfiguration Get(string name, Input<string> id, EndpointConfigurationState? state, CustomResourceOptions? opts = null)
public static EndpointConfiguration get(String name, Output<String> id, EndpointConfigurationState state, CustomResourceOptions options)
Resource lookup is not supported in YAML
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
resource_name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
The following state arguments are supported:
Arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

AsyncInferenceConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

DataCaptureConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

KmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

Name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

ProductionVariants List<Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantArgs>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

ShadowProductionVariants List<Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationShadowProductionVariantArgs>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

Tags Dictionary<string, string>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

TagsAll Dictionary<string, string>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

AsyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

DataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

KmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

Name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

ProductionVariants []EndpointConfigurationProductionVariantArgs

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

ShadowProductionVariants []EndpointConfigurationShadowProductionVariantArgs

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

Tags map[string]string

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

TagsAll map[string]string

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn String

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

asyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name String

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

productionVariants List<EndpointConfigurationProductionVariantArgs>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

shadowProductionVariants List<EndpointConfigurationShadowProductionVariantArgs>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Map<String,String>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

tagsAll Map<String,String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn string

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

asyncInferenceConfig EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name string

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

productionVariants EndpointConfigurationProductionVariantArgs[]

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

shadowProductionVariants EndpointConfigurationShadowProductionVariantArgs[]

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags {[key: string]: string}

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

tagsAll {[key: string]: string}

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn str

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

async_inference_config EndpointConfigurationAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

data_capture_config EndpointConfigurationDataCaptureConfigArgs

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kms_key_arn str

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name str

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

production_variants Sequence[EndpointConfigurationProductionVariantArgs]

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

shadow_production_variants Sequence[EndpointConfigurationShadowProductionVariantArgs]

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Mapping[str, str]

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

tags_all Mapping[str, str]

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

arn String

The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.

asyncInferenceConfig Property Map

Specifies configuration for how an endpoint performs asynchronous inference.

dataCaptureConfig Property Map

Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.

kmsKeyArn String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

name String

The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.

productionVariants List<Property Map>

An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.

shadowProductionVariants List<Property Map>

Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants.If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.

tags Map<String>

A mapping of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

tagsAll Map<String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Supporting Types

EndpointConfigurationAsyncInferenceConfig

OutputConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationAsyncInferenceConfigOutputConfig

Specifies the configuration for asynchronous inference invocation outputs.

ClientConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationAsyncInferenceConfigClientConfig

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

OutputConfig EndpointConfigurationAsyncInferenceConfigOutputConfig

Specifies the configuration for asynchronous inference invocation outputs.

ClientConfig EndpointConfigurationAsyncInferenceConfigClientConfig

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

outputConfig EndpointConfigurationAsyncInferenceConfigOutputConfig

Specifies the configuration for asynchronous inference invocation outputs.

clientConfig EndpointConfigurationAsyncInferenceConfigClientConfig

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

outputConfig EndpointConfigurationAsyncInferenceConfigOutputConfig

Specifies the configuration for asynchronous inference invocation outputs.

clientConfig EndpointConfigurationAsyncInferenceConfigClientConfig

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

output_config EndpointConfigurationAsyncInferenceConfigOutputConfig

Specifies the configuration for asynchronous inference invocation outputs.

client_config EndpointConfigurationAsyncInferenceConfigClientConfig

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

outputConfig Property Map

Specifies the configuration for asynchronous inference invocation outputs.

clientConfig Property Map

Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.

EndpointConfigurationAsyncInferenceConfigClientConfig

MaxConcurrentInvocationsPerInstance int

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

MaxConcurrentInvocationsPerInstance int

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance Integer

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance number

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

max_concurrent_invocations_per_instance int

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance Number

The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.

EndpointConfigurationAsyncInferenceConfigOutputConfig

S3OutputPath string

The Amazon S3 location to upload inference responses to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

NotificationConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

Specifies the configuration for notifications of inference results for asynchronous inference.

S3OutputPath string

The Amazon S3 location to upload inference responses to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

NotificationConfig EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

Specifies the configuration for notifications of inference results for asynchronous inference.

s3OutputPath String

The Amazon S3 location to upload inference responses to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

notificationConfig EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

Specifies the configuration for notifications of inference results for asynchronous inference.

s3OutputPath string

The Amazon S3 location to upload inference responses to.

kmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

notificationConfig EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

Specifies the configuration for notifications of inference results for asynchronous inference.

s3_output_path str

The Amazon S3 location to upload inference responses to.

kms_key_id str

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

notification_config EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

Specifies the configuration for notifications of inference results for asynchronous inference.

s3OutputPath String

The Amazon S3 location to upload inference responses to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.

notificationConfig Property Map

Specifies the configuration for notifications of inference results for asynchronous inference.

EndpointConfigurationAsyncInferenceConfigOutputConfigNotificationConfig

ErrorTopic string

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

SuccessTopic string

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

ErrorTopic string

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

SuccessTopic string

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic String

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

successTopic String

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic string

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

successTopic string

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

error_topic str

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

success_topic str

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic String

Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.

successTopic String

Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.

EndpointConfigurationDataCaptureConfig

CaptureOptions List<Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationDataCaptureConfigCaptureOption>

Specifies what data to capture. Fields are documented below.

DestinationS3Uri string

The URL for S3 location where the captured data is stored.

InitialSamplingPercentage int

Portion of data to capture. Should be between 0 and 100.

CaptureContentTypeHeader Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

The content type headers to capture. Fields are documented below.

EnableCapture bool

Flag to enable data capture. Defaults to false.

KmsKeyId string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

CaptureOptions []EndpointConfigurationDataCaptureConfigCaptureOption

Specifies what data to capture. Fields are documented below.

DestinationS3Uri string

The URL for S3 location where the captured data is stored.

InitialSamplingPercentage int

Portion of data to capture. Should be between 0 and 100.

CaptureContentTypeHeader EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

The content type headers to capture. Fields are documented below.

EnableCapture bool

Flag to enable data capture. Defaults to false.

KmsKeyId string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

captureOptions List<EndpointConfigurationDataCaptureConfigCaptureOption>

Specifies what data to capture. Fields are documented below.

destinationS3Uri String

The URL for S3 location where the captured data is stored.

initialSamplingPercentage Integer

Portion of data to capture. Should be between 0 and 100.

captureContentTypeHeader EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

The content type headers to capture. Fields are documented below.

enableCapture Boolean

Flag to enable data capture. Defaults to false.

kmsKeyId String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

captureOptions EndpointConfigurationDataCaptureConfigCaptureOption[]

Specifies what data to capture. Fields are documented below.

destinationS3Uri string

The URL for S3 location where the captured data is stored.

initialSamplingPercentage number

Portion of data to capture. Should be between 0 and 100.

captureContentTypeHeader EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

The content type headers to capture. Fields are documented below.

enableCapture boolean

Flag to enable data capture. Defaults to false.

kmsKeyId string

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

capture_options Sequence[EndpointConfigurationDataCaptureConfigCaptureOption]

Specifies what data to capture. Fields are documented below.

destination_s3_uri str

The URL for S3 location where the captured data is stored.

initial_sampling_percentage int

Portion of data to capture. Should be between 0 and 100.

capture_content_type_header EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

The content type headers to capture. Fields are documented below.

enable_capture bool

Flag to enable data capture. Defaults to false.

kms_key_id str

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

captureOptions List<Property Map>

Specifies what data to capture. Fields are documented below.

destinationS3Uri String

The URL for S3 location where the captured data is stored.

initialSamplingPercentage Number

Portion of data to capture. Should be between 0 and 100.

captureContentTypeHeader Property Map

The content type headers to capture. Fields are documented below.

enableCapture Boolean

Flag to enable data capture. Defaults to false.

kmsKeyId String

Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.

EndpointConfigurationDataCaptureConfigCaptureContentTypeHeader

CsvContentTypes List<string>

The CSV content type headers to capture.

JsonContentTypes List<string>

The JSON content type headers to capture.

CsvContentTypes []string

The CSV content type headers to capture.

JsonContentTypes []string

The JSON content type headers to capture.

csvContentTypes List<String>

The CSV content type headers to capture.

jsonContentTypes List<String>

The JSON content type headers to capture.

csvContentTypes string[]

The CSV content type headers to capture.

jsonContentTypes string[]

The JSON content type headers to capture.

csv_content_types Sequence[str]

The CSV content type headers to capture.

json_content_types Sequence[str]

The JSON content type headers to capture.

csvContentTypes List<String>

The CSV content type headers to capture.

jsonContentTypes List<String>

The JSON content type headers to capture.

EndpointConfigurationDataCaptureConfigCaptureOption

CaptureMode string

Specifies the data to be captured. Should be one of Input or Output.

CaptureMode string

Specifies the data to be captured. Should be one of Input or Output.

captureMode String

Specifies the data to be captured. Should be one of Input or Output.

captureMode string

Specifies the data to be captured. Should be one of Input or Output.

capture_mode str

Specifies the data to be captured. Should be one of Input or Output.

captureMode String

Specifies the data to be captured. Should be one of Input or Output.

EndpointConfigurationProductionVariant

ModelName string

The name of the model to use.

AcceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

ContainerStartupHealthCheckTimeoutInSeconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

CoreDumpConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

InitialInstanceCount int

Initial number of instances used for auto-scaling.

InitialVariantWeight double

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

InstanceType string

The type of instance to start.

ModelDataDownloadTimeoutInSeconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

ServerlessConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

VariantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

VolumeSizeInGb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

ModelName string

The name of the model to use.

AcceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

ContainerStartupHealthCheckTimeoutInSeconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

CoreDumpConfig EndpointConfigurationProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

InitialInstanceCount int

Initial number of instances used for auto-scaling.

InitialVariantWeight float64

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

InstanceType string

The type of instance to start.

ModelDataDownloadTimeoutInSeconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

ServerlessConfig EndpointConfigurationProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

VariantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

VolumeSizeInGb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName String

The name of the model to use.

acceleratorType String

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds Integer

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig EndpointConfigurationProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount Integer

Initial number of instances used for auto-scaling.

initialVariantWeight Double

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType String

The type of instance to start.

modelDataDownloadTimeoutInSeconds Integer

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig EndpointConfigurationProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variantName String

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb Integer

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName string

The name of the model to use.

acceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds number

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig EndpointConfigurationProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount number

Initial number of instances used for auto-scaling.

initialVariantWeight number

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType string

The type of instance to start.

modelDataDownloadTimeoutInSeconds number

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig EndpointConfigurationProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb number

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

model_name str

The name of the model to use.

accelerator_type str

The size of the Elastic Inference (EI) instance to use for the production variant.

container_startup_health_check_timeout_in_seconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

core_dump_config EndpointConfigurationProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initial_instance_count int

Initial number of instances used for auto-scaling.

initial_variant_weight float

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instance_type str

The type of instance to start.

model_data_download_timeout_in_seconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverless_config EndpointConfigurationProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variant_name str

The name of the variant. If omitted, this provider will assign a random, unique name.

volume_size_in_gb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName String

The name of the model to use.

acceleratorType String

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds Number

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig Property Map

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount Number

Initial number of instances used for auto-scaling.

initialVariantWeight Number

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType String

The type of instance to start.

modelDataDownloadTimeoutInSeconds Number

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig Property Map

Specifies configuration for how an endpoint performs asynchronous inference.

variantName String

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb Number

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

EndpointConfigurationProductionVariantCoreDumpConfig

DestinationS3Uri string

The Amazon S3 bucket to send the core dump to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

DestinationS3Uri string

The Amazon S3 bucket to send the core dump to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri String

The Amazon S3 bucket to send the core dump to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri string

The Amazon S3 bucket to send the core dump to.

kmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destination_s3_uri str

The Amazon S3 bucket to send the core dump to.

kms_key_id str

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri String

The Amazon S3 bucket to send the core dump to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

EndpointConfigurationProductionVariantServerlessConfig

MaxConcurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

MemorySizeInMb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

MaxConcurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

MemorySizeInMb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency Integer

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb Integer

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency number

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb number

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

max_concurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memory_size_in_mb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency Number

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb Number

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

EndpointConfigurationShadowProductionVariant

ModelName string

The name of the model to use.

AcceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

ContainerStartupHealthCheckTimeoutInSeconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

CoreDumpConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationShadowProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

InitialInstanceCount int

Initial number of instances used for auto-scaling.

InitialVariantWeight double

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

InstanceType string

The type of instance to start.

ModelDataDownloadTimeoutInSeconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

ServerlessConfig Pulumi.Aws.Sagemaker.Inputs.EndpointConfigurationShadowProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

VariantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

VolumeSizeInGb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

ModelName string

The name of the model to use.

AcceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

ContainerStartupHealthCheckTimeoutInSeconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

CoreDumpConfig EndpointConfigurationShadowProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

InitialInstanceCount int

Initial number of instances used for auto-scaling.

InitialVariantWeight float64

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

InstanceType string

The type of instance to start.

ModelDataDownloadTimeoutInSeconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

ServerlessConfig EndpointConfigurationShadowProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

VariantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

VolumeSizeInGb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName String

The name of the model to use.

acceleratorType String

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds Integer

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig EndpointConfigurationShadowProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount Integer

Initial number of instances used for auto-scaling.

initialVariantWeight Double

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType String

The type of instance to start.

modelDataDownloadTimeoutInSeconds Integer

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig EndpointConfigurationShadowProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variantName String

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb Integer

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName string

The name of the model to use.

acceleratorType string

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds number

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig EndpointConfigurationShadowProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount number

Initial number of instances used for auto-scaling.

initialVariantWeight number

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType string

The type of instance to start.

modelDataDownloadTimeoutInSeconds number

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig EndpointConfigurationShadowProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variantName string

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb number

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

model_name str

The name of the model to use.

accelerator_type str

The size of the Elastic Inference (EI) instance to use for the production variant.

container_startup_health_check_timeout_in_seconds int

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

core_dump_config EndpointConfigurationShadowProductionVariantCoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initial_instance_count int

Initial number of instances used for auto-scaling.

initial_variant_weight float

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instance_type str

The type of instance to start.

model_data_download_timeout_in_seconds int

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverless_config EndpointConfigurationShadowProductionVariantServerlessConfig

Specifies configuration for how an endpoint performs asynchronous inference.

variant_name str

The name of the variant. If omitted, this provider will assign a random, unique name.

volume_size_in_gb int

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

modelName String

The name of the model to use.

acceleratorType String

The size of the Elastic Inference (EI) instance to use for the production variant.

containerStartupHealthCheckTimeoutInSeconds Number

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.

coreDumpConfig Property Map

Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.

initialInstanceCount Number

Initial number of instances used for auto-scaling.

initialVariantWeight Number

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.

instanceType String

The type of instance to start.

modelDataDownloadTimeoutInSeconds Number

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.

serverlessConfig Property Map

Specifies configuration for how an endpoint performs asynchronous inference.

variantName String

The name of the variant. If omitted, this provider will assign a random, unique name.

volumeSizeInGb Number

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.

EndpointConfigurationShadowProductionVariantCoreDumpConfig

DestinationS3Uri string

The Amazon S3 bucket to send the core dump to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

DestinationS3Uri string

The Amazon S3 bucket to send the core dump to.

KmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri String

The Amazon S3 bucket to send the core dump to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri string

The Amazon S3 bucket to send the core dump to.

kmsKeyId string

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destination_s3_uri str

The Amazon S3 bucket to send the core dump to.

kms_key_id str

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

destinationS3Uri String

The Amazon S3 bucket to send the core dump to.

kmsKeyId String

The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.

EndpointConfigurationShadowProductionVariantServerlessConfig

MaxConcurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

MemorySizeInMb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

MaxConcurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

MemorySizeInMb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency Integer

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb Integer

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency number

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb number

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

max_concurrency int

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memory_size_in_mb int

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

maxConcurrency Number

The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.

memorySizeInMb Number

The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

Import

Endpoint configurations can be imported using the name, e.g.,

 $ pulumi import aws:sagemaker/endpointConfiguration:EndpointConfiguration test_endpoint_config endpoint-config-foo

Package Details

Repository
AWS Classic pulumi/pulumi-aws
License
Apache-2.0
Notes

This Pulumi package is based on the aws Terraform Provider.