Sign in Dashboard Get started
  1. Registry
  2. Packages
  3. AWS
  4. API Docs
  5. sagemaker
  6. InferenceComponent
Viewing docs for AWS v7.52.1
published on Wednesday, Oct 28, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-aws

aws.sagemaker.InferenceComponent

aws logo aws logo
Viewing docs for AWS v7.52.1
published on Wednesday, Oct 28, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-aws

    Provides a SageMaker AI Inference Component resource. An inference component is a SageMaker AI hosting object that you can use to deploy a model to an endpoint. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model.

    Example Usage

    Basic Usage

    import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.sagemaker.InferenceComponent("example", {
    specification: {
        computeResourceRequirements: {
            minMemoryRequiredInMb: 1024,
        },
        modelName: exampleAwsSagemakerModel.name,
    },
    runtimeConfig: {
        copyCount: 1,
    },
    name: "my-inference-component",
    endpointName: exampleAwsSagemakerEndpoint.name,
    variantName: "variant-1",
});

    import pulumi
import pulumi_aws as aws

example = aws.sagemaker.InferenceComponent("example",
    specification={
        "compute_resource_requirements": {
            "min_memory_required_in_mb": 1024,
        },
        "model_name": example_aws_sagemaker_model["name"],
    },
    runtime_config={
        "copy_count": 1,
    },
    name="my-inference-component",
    endpoint_name=example_aws_sagemaker_endpoint["name"],
    variant_name="variant-1")

    package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v7/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewInferenceComponent(ctx, "example", &sagemaker.InferenceComponentArgs{
			Specification: &sagemaker.InferenceComponentSpecificationArgs{
				ComputeResourceRequirements: &sagemaker.InferenceComponentSpecificationComputeResourceRequirementsArgs{
					MinMemoryRequiredInMb: pulumi.Int(1024),
				},
				ModelName: pulumi.Any(exampleAwsSagemakerModel.Name),
			},
			RuntimeConfig: &sagemaker.InferenceComponentRuntimeConfigArgs{
				CopyCount: pulumi.Int(1),
			},
			Name:         pulumi.String("my-inference-component"),
			EndpointName: pulumi.Any(exampleAwsSagemakerEndpoint.Name),
			VariantName:  pulumi.String("variant-1"),
		})
		if err != nil {
			return err
		}
		return nil
	})
}

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Sagemaker.InferenceComponent("example", new()
    {
        Specification = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationArgs
        {
            ComputeResourceRequirements = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs
            {
                MinMemoryRequiredInMb = 1024,
            },
            ModelName = exampleAwsSagemakerModel.Name,
        },
        RuntimeConfig = new Aws.Sagemaker.Inputs.InferenceComponentRuntimeConfigArgs
        {
            CopyCount = 1,
        },
        Name = "my-inference-component",
        EndpointName = exampleAwsSagemakerEndpoint.Name,
        VariantName = "variant-1",
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.InferenceComponent;
import com.pulumi.aws.sagemaker.InferenceComponentArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentRuntimeConfigArgs;
import java.util.ArrayList;
import java.util.Arrays;
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 example = new InferenceComponent("example", InferenceComponentArgs.builder()
            .specification(InferenceComponentSpecificationArgs.builder()
                .computeResourceRequirements(InferenceComponentSpecificationComputeResourceRequirementsArgs.builder()
                    .minMemoryRequiredInMb(1024)
                    .build())
                .modelName(exampleAwsSagemakerModel.get("name"))
                .build())
            .runtimeConfig(InferenceComponentRuntimeConfigArgs.builder()
                .copyCount(1)
                .build())
            .name("my-inference-component")
            .endpointName(exampleAwsSagemakerEndpoint.get("name"))
            .variantName("variant-1")
            .build());

    }
}

    resources:
  example:
    type: aws:sagemaker:InferenceComponent
    properties:
      specification:
        computeResourceRequirements:
          minMemoryRequiredInMb: 1024
        modelName: ${exampleAwsSagemakerModel.name}
      runtimeConfig:
        copyCount: 1
      name: my-inference-component
      endpointName: ${exampleAwsSagemakerEndpoint.name}
      variantName: variant-1

    terraform {
  required_providers {
    aws = {
      source = "pulumi/aws"
    }
  }
}

resource "aws_sagemaker_inference_component" "example" {
  lifecycle {
    create_before_destroy = true
  }
  specification {
    compute_resource_requirements {
      min_memory_required_in_mb = 1024
    }
    model_name = exampleAwsSagemakerModel.name
  }
  runtime_config {
    copy_count = 1
  }
  name          = "my-inference-component"
  endpoint_name = exampleAwsSagemakerEndpoint.name
  variant_name  = "variant-1"
}

    With Container Specification

    import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.sagemaker.InferenceComponent("example", {
    specification: {
        container: {
            image: "123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest",
            artifactUrl: "s3://my-bucket/model.tar.gz",
            environment: {
                MODEL_NAME: "my-model",
            },
        },
        computeResourceRequirements: {
            minMemoryRequiredInMb: 2048,
            maxMemoryRequiredInMb: 4096,
            numberOfCpuCoresRequired: 2,
            numberOfAcceleratorDevicesRequired: 1,
        },
        startupParameters: {
            containerStartupHealthCheckTimeoutInSeconds: 300,
            modelDataDownloadTimeoutInSeconds: 300,
        },
    },
    runtimeConfig: {
        copyCount: 2,
    },
    name: "my-inference-component",
    endpointName: exampleAwsSagemakerEndpoint.name,
    variantName: "variant-1",
});

    import pulumi
import pulumi_aws as aws

example = aws.sagemaker.InferenceComponent("example",
    specification={
        "container": {
            "image": "123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest",
            "artifact_url": "s3://my-bucket/model.tar.gz",
            "environment": {
                "MODEL_NAME": "my-model",
            },
        },
        "compute_resource_requirements": {
            "min_memory_required_in_mb": 2048,
            "max_memory_required_in_mb": 4096,
            "number_of_cpu_cores_required": float(2),
            "number_of_accelerator_devices_required": float(1),
        },
        "startup_parameters": {
            "container_startup_health_check_timeout_in_seconds": 300,
            "model_data_download_timeout_in_seconds": 300,
        },
    },
    runtime_config={
        "copy_count": 2,
    },
    name="my-inference-component",
    endpoint_name=example_aws_sagemaker_endpoint["name"],
    variant_name="variant-1")

    package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v7/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewInferenceComponent(ctx, "example", &sagemaker.InferenceComponentArgs{
			Specification: &sagemaker.InferenceComponentSpecificationArgs{
				Container: &sagemaker.InferenceComponentSpecificationContainerArgs{
					Image:       pulumi.String("123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest"),
					ArtifactUrl: pulumi.String("s3://my-bucket/model.tar.gz"),
					Environment: pulumi.StringMap{
						"MODEL_NAME": pulumi.String("my-model"),
					},
				},
				ComputeResourceRequirements: &sagemaker.InferenceComponentSpecificationComputeResourceRequirementsArgs{
					MinMemoryRequiredInMb:              pulumi.Int(2048),
					MaxMemoryRequiredInMb:              pulumi.Int(4096),
					NumberOfCpuCoresRequired:           pulumi.Float64(2),
					NumberOfAcceleratorDevicesRequired: pulumi.Float64(1),
				},
				StartupParameters: &sagemaker.InferenceComponentSpecificationStartupParametersArgs{
					ContainerStartupHealthCheckTimeoutInSeconds: pulumi.Int(300),
					ModelDataDownloadTimeoutInSeconds:           pulumi.Int(300),
				},
			},
			RuntimeConfig: &sagemaker.InferenceComponentRuntimeConfigArgs{
				CopyCount: pulumi.Int(2),
			},
			Name:         pulumi.String("my-inference-component"),
			EndpointName: pulumi.Any(exampleAwsSagemakerEndpoint.Name),
			VariantName:  pulumi.String("variant-1"),
		})
		if err != nil {
			return err
		}
		return nil
	})
}

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Sagemaker.InferenceComponent("example", new()
    {
        Specification = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationArgs
        {
            Container = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerArgs
            {
                Image = "123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest",
                ArtifactUrl = "s3://my-bucket/model.tar.gz",
                Environment = 
                {
                    { "MODEL_NAME", "my-model" },
                },
            },
            ComputeResourceRequirements = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs
            {
                MinMemoryRequiredInMb = 2048,
                MaxMemoryRequiredInMb = 4096,
                NumberOfCpuCoresRequired = 2.0,
                NumberOfAcceleratorDevicesRequired = 1.0,
            },
            StartupParameters = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationStartupParametersArgs
            {
                ContainerStartupHealthCheckTimeoutInSeconds = 300,
                ModelDataDownloadTimeoutInSeconds = 300,
            },
        },
        RuntimeConfig = new Aws.Sagemaker.Inputs.InferenceComponentRuntimeConfigArgs
        {
            CopyCount = 2,
        },
        Name = "my-inference-component",
        EndpointName = exampleAwsSagemakerEndpoint.Name,
        VariantName = "variant-1",
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.InferenceComponent;
import com.pulumi.aws.sagemaker.InferenceComponentArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationContainerArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationStartupParametersArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentRuntimeConfigArgs;
import java.util.ArrayList;
import java.util.Arrays;
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 example = new InferenceComponent("example", InferenceComponentArgs.builder()
            .specification(InferenceComponentSpecificationArgs.builder()
                .container(InferenceComponentSpecificationContainerArgs.builder()
                    .image("123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest")
                    .artifactUrl("s3://my-bucket/model.tar.gz")
                    .environment(Map.of("MODEL_NAME", "my-model"))
                    .build())
                .computeResourceRequirements(InferenceComponentSpecificationComputeResourceRequirementsArgs.builder()
                    .minMemoryRequiredInMb(2048)
                    .maxMemoryRequiredInMb(4096)
                    .numberOfCpuCoresRequired(2.0)
                    .numberOfAcceleratorDevicesRequired(1.0)
                    .build())
                .startupParameters(InferenceComponentSpecificationStartupParametersArgs.builder()
                    .containerStartupHealthCheckTimeoutInSeconds(300)
                    .modelDataDownloadTimeoutInSeconds(300)
                    .build())
                .build())
            .runtimeConfig(InferenceComponentRuntimeConfigArgs.builder()
                .copyCount(2)
                .build())
            .name("my-inference-component")
            .endpointName(exampleAwsSagemakerEndpoint.get("name"))
            .variantName("variant-1")
            .build());

    }
}

    resources:
  example:
    type: aws:sagemaker:InferenceComponent
    properties:
      specification:
        container:
          image: 123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest
          artifactUrl: s3://my-bucket/model.tar.gz
          environment:
            MODEL_NAME: my-model
        computeResourceRequirements:
          minMemoryRequiredInMb: 2048
          maxMemoryRequiredInMb: 4096
          numberOfCpuCoresRequired: 2
          numberOfAcceleratorDevicesRequired: 1
        startupParameters:
          containerStartupHealthCheckTimeoutInSeconds: 300
          modelDataDownloadTimeoutInSeconds: 300
      runtimeConfig:
        copyCount: 2
      name: my-inference-component
      endpointName: ${exampleAwsSagemakerEndpoint.name}
      variantName: variant-1

    terraform {
  required_providers {
    aws = {
      source = "pulumi/aws"
    }
  }
}

resource "aws_sagemaker_inference_component" "example" {
  lifecycle {
    create_before_destroy = true
  }
  specification {
    container {
      image        = "123456789012.dkr.ecr.us-east-1.amazonaws.com/my-model:latest"
      artifact_url = "s3://my-bucket/model.tar.gz"
      environment = {
        "MODEL_NAME" = "my-model"
      }
    }
    compute_resource_requirements {
      min_memory_required_in_mb              = 2048
      max_memory_required_in_mb              = 4096
      number_of_cpu_cores_required           = 2
      number_of_accelerator_devices_required = 1
    }
    startup_parameters {
      container_startup_health_check_timeout_in_seconds = 300
      model_data_download_timeout_in_seconds            = 300
    }
  }
  runtime_config {
    copy_count = 2
  }
  name          = "my-inference-component"
  endpoint_name = exampleAwsSagemakerEndpoint.name
  variant_name  = "variant-1"
}

    With Deployment Config

    deploymentConfig controls how updates to an existing inference component are rolled out; it has no effect on the initial create. Add it (or change it) on a subsequent apply to govern the rollout of a specification or runtimeConfig change.

    import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.sagemaker.InferenceComponent("example", {
    specification: {
        computeResourceRequirements: {
            minMemoryRequiredInMb: 1024,
        },
        modelName: exampleAwsSagemakerModel.name,
    },
    runtimeConfig: {
        copyCount: 4,
    },
    deploymentConfig: {
        rollingUpdatePolicy: {
            maximumBatchSize: {
                type: "COPY_COUNT",
                value: 1,
            },
            waitIntervalInSeconds: 60,
        },
        autoRollbackConfiguration: {
            alarms: [{
                alarmName: exampleAwsCloudwatchMetricAlarm.alarmName,
            }],
        },
    },
    name: "my-inference-component",
    endpointName: exampleAwsSagemakerEndpoint.name,
    variantName: "variant-1",
});

    import pulumi
import pulumi_aws as aws

example = aws.sagemaker.InferenceComponent("example",
    specification={
        "compute_resource_requirements": {
            "min_memory_required_in_mb": 1024,
        },
        "model_name": example_aws_sagemaker_model["name"],
    },
    runtime_config={
        "copy_count": 4,
    },
    deployment_config={
        "rolling_update_policy": {
            "maximum_batch_size": {
                "type": "COPY_COUNT",
                "value": 1,
            },
            "wait_interval_in_seconds": 60,
        },
        "auto_rollback_configuration": {
            "alarms": [{
                "alarm_name": example_aws_cloudwatch_metric_alarm["alarmName"],
            }],
        },
    },
    name="my-inference-component",
    endpoint_name=example_aws_sagemaker_endpoint["name"],
    variant_name="variant-1")

    package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v7/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewInferenceComponent(ctx, "example", &sagemaker.InferenceComponentArgs{
			Specification: &sagemaker.InferenceComponentSpecificationArgs{
				ComputeResourceRequirements: &sagemaker.InferenceComponentSpecificationComputeResourceRequirementsArgs{
					MinMemoryRequiredInMb: pulumi.Int(1024),
				},
				ModelName: pulumi.Any(exampleAwsSagemakerModel.Name),
			},
			RuntimeConfig: &sagemaker.InferenceComponentRuntimeConfigArgs{
				CopyCount: pulumi.Int(4),
			},
			DeploymentConfig: &sagemaker.InferenceComponentDeploymentConfigArgs{
				RollingUpdatePolicy: &sagemaker.InferenceComponentDeploymentConfigRollingUpdatePolicyArgs{
					MaximumBatchSize: &sagemaker.InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs{
						Type:  pulumi.String("COPY_COUNT"),
						Value: pulumi.Int(1),
					},
					WaitIntervalInSeconds: pulumi.Int(60),
				},
				AutoRollbackConfiguration: &sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs{
					Alarms: sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArray{
						&sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs{
							AlarmName: pulumi.Any(exampleAwsCloudwatchMetricAlarm.AlarmName),
						},
					},
				},
			},
			Name:         pulumi.String("my-inference-component"),
			EndpointName: pulumi.Any(exampleAwsSagemakerEndpoint.Name),
			VariantName:  pulumi.String("variant-1"),
		})
		if err != nil {
			return err
		}
		return nil
	})
}

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Sagemaker.InferenceComponent("example", new()
    {
        Specification = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationArgs
        {
            ComputeResourceRequirements = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs
            {
                MinMemoryRequiredInMb = 1024,
            },
            ModelName = exampleAwsSagemakerModel.Name,
        },
        RuntimeConfig = new Aws.Sagemaker.Inputs.InferenceComponentRuntimeConfigArgs
        {
            CopyCount = 4,
        },
        DeploymentConfig = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigArgs
        {
            RollingUpdatePolicy = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyArgs
            {
                MaximumBatchSize = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs
                {
                    Type = "COPY_COUNT",
                    Value = 1,
                },
                WaitIntervalInSeconds = 60,
            },
            AutoRollbackConfiguration = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs
            {
                Alarms = new[]
                {
                    new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs
                    {
                        AlarmName = exampleAwsCloudwatchMetricAlarm.AlarmName,
                    },
                },
            },
        },
        Name = "my-inference-component",
        EndpointName = exampleAwsSagemakerEndpoint.Name,
        VariantName = "variant-1",
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.InferenceComponent;
import com.pulumi.aws.sagemaker.InferenceComponentArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentRuntimeConfigArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentDeploymentConfigArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs;
import com.pulumi.aws.sagemaker.inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs;
import java.util.ArrayList;
import java.util.Arrays;
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 example = new InferenceComponent("example", InferenceComponentArgs.builder()
            .specification(InferenceComponentSpecificationArgs.builder()
                .computeResourceRequirements(InferenceComponentSpecificationComputeResourceRequirementsArgs.builder()
                    .minMemoryRequiredInMb(1024)
                    .build())
                .modelName(exampleAwsSagemakerModel.get("name"))
                .build())
            .runtimeConfig(InferenceComponentRuntimeConfigArgs.builder()
                .copyCount(4)
                .build())
            .deploymentConfig(InferenceComponentDeploymentConfigArgs.builder()
                .rollingUpdatePolicy(InferenceComponentDeploymentConfigRollingUpdatePolicyArgs.builder()
                    .maximumBatchSize(InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs.builder()
                        .type("COPY_COUNT")
                        .value(1)
                        .build())
                    .waitIntervalInSeconds(60)
                    .build())
                .autoRollbackConfiguration(InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs.builder()
                    .alarms(InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs.builder()
                        .alarmName(exampleAwsCloudwatchMetricAlarm.get("alarmName"))
                        .build())
                    .build())
                .build())
            .name("my-inference-component")
            .endpointName(exampleAwsSagemakerEndpoint.get("name"))
            .variantName("variant-1")
            .build());

    }
}

    resources:
  example:
    type: aws:sagemaker:InferenceComponent
    properties:
      specification:
        computeResourceRequirements:
          minMemoryRequiredInMb: 1024
        modelName: ${exampleAwsSagemakerModel.name}
      runtimeConfig:
        copyCount: 4
      deploymentConfig:
        rollingUpdatePolicy:
          maximumBatchSize:
            type: COPY_COUNT
            value: 1
          waitIntervalInSeconds: 60
        autoRollbackConfiguration:
          alarms:
            - alarmName: ${exampleAwsCloudwatchMetricAlarm.alarmName}
      name: my-inference-component
      endpointName: ${exampleAwsSagemakerEndpoint.name}
      variantName: variant-1

    terraform {
  required_providers {
    aws = {
      source = "pulumi/aws"
    }
  }
}

resource "aws_sagemaker_inference_component" "example" {
  lifecycle {
    create_before_destroy = true
  }
  specification {
    compute_resource_requirements {
      min_memory_required_in_mb = 1024
    }
    model_name = exampleAwsSagemakerModel.name
  }
  runtime_config {
    copy_count = 4
  }
  deployment_config {
    rolling_update_policy {
      maximum_batch_size {
        type  = "COPY_COUNT"
        value = 1
      }
      wait_interval_in_seconds = 60
    }
    auto_rollback_configuration {
      alarms {
        alarm_name = exampleAwsCloudwatchMetricAlarm.alarmName
      }
    }
  }
  name          = "my-inference-component"
  endpoint_name = exampleAwsSagemakerEndpoint.name
  variant_name  = "variant-1"
}

    Create InferenceComponent Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new InferenceComponent(name: string, args: InferenceComponentArgs, opts?: CustomResourceOptions);
    @overload
def InferenceComponent(resource_name: str,
                       args: InferenceComponentArgs,
                       opts: Optional[ResourceOptions] = None)

@overload
def InferenceComponent(resource_name: str,
                       opts: Optional[ResourceOptions] = None,
                       endpoint_name: Optional[str] = None,
                       deployment_config: Optional[InferenceComponentDeploymentConfigArgs] = None,
                       name: Optional[str] = None,
                       region: Optional[str] = None,
                       runtime_config: Optional[InferenceComponentRuntimeConfigArgs] = None,
                       specification: Optional[InferenceComponentSpecificationArgs] = None,
                       specifications: Optional[Sequence[InferenceComponentSpecificationArgs]] = None,
                       tags: Optional[Mapping[str, str]] = None,
                       timeouts: Optional[InferenceComponentTimeoutsArgs] = None,
                       variant_name: Optional[str] = None)
    func NewInferenceComponent(ctx *Context, name string, args InferenceComponentArgs, opts ...ResourceOption) (*InferenceComponent, error)
    public InferenceComponent(string name, InferenceComponentArgs args, CustomResourceOptions? opts = null)
    public InferenceComponent(String name, InferenceComponentArgs args)
public InferenceComponent(String name, InferenceComponentArgs args, CustomResourceOptions options)

    type: aws:sagemaker:InferenceComponent
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.


    resource "aws_sagemaker_inference_component" "name" {
    # resource properties
}

    Parameters

    name string
    The unique name of the resource.
    args InferenceComponentArgs
    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 InferenceComponentArgs
    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 InferenceComponentArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args InferenceComponentArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args InferenceComponentArgs
    The arguments to resource properties.
    options CustomResourceOptions
    Bag of options to control resource's behavior.

    Constructor example

    The following reference example uses placeholder values for all input properties.

    var inferenceComponentResource = new Aws.Sagemaker.InferenceComponent("inferenceComponentResource", new()
{
    EndpointName = "string",
    DeploymentConfig = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigArgs
    {
        RollingUpdatePolicy = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyArgs
        {
            MaximumBatchSize = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs
            {
                Type = "string",
                Value = 0,
            },
            WaitIntervalInSeconds = 0,
            MaximumExecutionTimeoutInSeconds = 0,
            RollbackMaximumBatchSize = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs
            {
                Type = "string",
                Value = 0,
            },
        },
        AutoRollbackConfiguration = new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs
        {
            Alarms = new[]
            {
                new Aws.Sagemaker.Inputs.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs
                {
                    AlarmName = "string",
                },
            },
        },
    },
    Name = "string",
    Region = "string",
    RuntimeConfig = new Aws.Sagemaker.Inputs.InferenceComponentRuntimeConfigArgs
    {
        CopyCount = 0,
        CurrentCopyCount = 0,
        DesiredCopyCount = 0,
        PlacementStatuses = new[]
        {
            new Aws.Sagemaker.Inputs.InferenceComponentRuntimeConfigPlacementStatusArgs
            {
                CurrentCopyCount = 0,
                InstanceType = "string",
            },
        },
    },
    Specification = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationArgs
    {
        BaseInferenceComponentName = "string",
        ComputeResourceRequirements = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs
        {
            MinMemoryRequiredInMb = 0,
            MaxMemoryRequiredInMb = 0,
            NumberOfAcceleratorDevicesRequired = 0.0,
            NumberOfCpuCoresRequired = 0.0,
        },
        Container = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerArgs
        {
            ArtifactUrl = "string",
            ContainerMetricsConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerContainerMetricsConfigArgs
            {
                MetricsEndpoint = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs
                {
                    MetricsEndpointPath = "string",
                    MetricPublishFrequencyInSeconds = 0,
                },
            },
            Environment = 
            {
                { "string", "string" },
            },
            Image = "string",
            ResolvedImage = "string",
        },
        DataCacheConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationDataCacheConfigArgs
        {
            EnableCaching = false,
        },
        InstanceType = "string",
        ModelName = "string",
        SchedulingConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationSchedulingConfigArgs
        {
            PlacementStrategy = "string",
            AvailabilityZoneBalance = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs
            {
                EnforcementMode = "string",
                MaxImbalance = 0,
            },
        },
        StartupParameters = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationStartupParametersArgs
        {
            ContainerStartupHealthCheckTimeoutInSeconds = 0,
            ModelDataDownloadTimeoutInSeconds = 0,
        },
    },
    Specifications = new[]
    {
        new Aws.Sagemaker.Inputs.InferenceComponentSpecificationArgs
        {
            BaseInferenceComponentName = "string",
            ComputeResourceRequirements = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationComputeResourceRequirementsArgs
            {
                MinMemoryRequiredInMb = 0,
                MaxMemoryRequiredInMb = 0,
                NumberOfAcceleratorDevicesRequired = 0.0,
                NumberOfCpuCoresRequired = 0.0,
            },
            Container = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerArgs
            {
                ArtifactUrl = "string",
                ContainerMetricsConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerContainerMetricsConfigArgs
                {
                    MetricsEndpoint = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs
                    {
                        MetricsEndpointPath = "string",
                        MetricPublishFrequencyInSeconds = 0,
                    },
                },
                Environment = 
                {
                    { "string", "string" },
                },
                Image = "string",
                ResolvedImage = "string",
            },
            DataCacheConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationDataCacheConfigArgs
            {
                EnableCaching = false,
            },
            InstanceType = "string",
            ModelName = "string",
            SchedulingConfig = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationSchedulingConfigArgs
            {
                PlacementStrategy = "string",
                AvailabilityZoneBalance = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs
                {
                    EnforcementMode = "string",
                    MaxImbalance = 0,
                },
            },
            StartupParameters = new Aws.Sagemaker.Inputs.InferenceComponentSpecificationStartupParametersArgs
            {
                ContainerStartupHealthCheckTimeoutInSeconds = 0,
                ModelDataDownloadTimeoutInSeconds = 0,
            },
        },
    },
    Tags = 
    {
        { "string", "string" },
    },
    Timeouts = new Aws.Sagemaker.Inputs.InferenceComponentTimeoutsArgs
    {
        Create = "string",
        Delete = "string",
        Update = "string",
    },
    VariantName = "string",
});

    example, err := sagemaker.NewInferenceComponent(ctx, "inferenceComponentResource", &sagemaker.InferenceComponentArgs{
	EndpointName: pulumi.String("string"),
	DeploymentConfig: &sagemaker.InferenceComponentDeploymentConfigArgs{
		RollingUpdatePolicy: &sagemaker.InferenceComponentDeploymentConfigRollingUpdatePolicyArgs{
			MaximumBatchSize: &sagemaker.InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs{
				Type:  pulumi.String("string"),
				Value: pulumi.Int(0),
			},
			WaitIntervalInSeconds:            pulumi.Int(0),
			MaximumExecutionTimeoutInSeconds: pulumi.Int(0),
			RollbackMaximumBatchSize: &sagemaker.InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs{
				Type:  pulumi.String("string"),
				Value: pulumi.Int(0),
			},
		},
		AutoRollbackConfiguration: &sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs{
			Alarms: sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArray{
				&sagemaker.InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs{
					AlarmName: pulumi.String("string"),
				},
			},
		},
	},
	Name:   pulumi.String("string"),
	Region: pulumi.String("string"),
	RuntimeConfig: &sagemaker.InferenceComponentRuntimeConfigArgs{
		CopyCount:        pulumi.Int(0),
		CurrentCopyCount: pulumi.Int(0),
		DesiredCopyCount: pulumi.Int(0),
		PlacementStatuses: sagemaker.InferenceComponentRuntimeConfigPlacementStatusArray{
			&sagemaker.InferenceComponentRuntimeConfigPlacementStatusArgs{
				CurrentCopyCount: pulumi.Int(0),
				InstanceType:     pulumi.String("string"),
			},
		},
	},
	Specification: &sagemaker.InferenceComponentSpecificationArgs{
		BaseInferenceComponentName: pulumi.String("string"),
		ComputeResourceRequirements: &sagemaker.InferenceComponentSpecificationComputeResourceRequirementsArgs{
			MinMemoryRequiredInMb:              pulumi.Int(0),
			MaxMemoryRequiredInMb:              pulumi.Int(0),
			NumberOfAcceleratorDevicesRequired: pulumi.Float64(0),
			NumberOfCpuCoresRequired:           pulumi.Float64(0),
		},
		Container: &sagemaker.InferenceComponentSpecificationContainerArgs{
			ArtifactUrl: pulumi.String("string"),
			ContainerMetricsConfig: &sagemaker.InferenceComponentSpecificationContainerContainerMetricsConfigArgs{
				MetricsEndpoint: &sagemaker.InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs{
					MetricsEndpointPath:             pulumi.String("string"),
					MetricPublishFrequencyInSeconds: pulumi.Int(0),
				},
			},
			Environment: pulumi.StringMap{
				"string": pulumi.String("string"),
			},
			Image:         pulumi.String("string"),
			ResolvedImage: pulumi.String("string"),
		},
		DataCacheConfig: &sagemaker.InferenceComponentSpecificationDataCacheConfigArgs{
			EnableCaching: pulumi.Bool(false),
		},
		InstanceType: pulumi.String("string"),
		ModelName:    pulumi.String("string"),
		SchedulingConfig: &sagemaker.InferenceComponentSpecificationSchedulingConfigArgs{
			PlacementStrategy: pulumi.String("string"),
			AvailabilityZoneBalance: &sagemaker.InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs{
				EnforcementMode: pulumi.String("string"),
				MaxImbalance:    pulumi.Int(0),
			},
		},
		StartupParameters: &sagemaker.InferenceComponentSpecificationStartupParametersArgs{
			ContainerStartupHealthCheckTimeoutInSeconds: pulumi.Int(0),
			ModelDataDownloadTimeoutInSeconds:           pulumi.Int(0),
		},
	},
	Specifications: sagemaker.InferenceComponentSpecificationArray{
		&sagemaker.InferenceComponentSpecificationArgs{
			BaseInferenceComponentName: pulumi.String("string"),
			ComputeResourceRequirements: &sagemaker.InferenceComponentSpecificationComputeResourceRequirementsArgs{
				MinMemoryRequiredInMb:              pulumi.Int(0),
				MaxMemoryRequiredInMb:              pulumi.Int(0),
				NumberOfAcceleratorDevicesRequired: pulumi.Float64(0),
				NumberOfCpuCoresRequired:           pulumi.Float64(0),
			},
			Container: &sagemaker.InferenceComponentSpecificationContainerArgs{
				ArtifactUrl: pulumi.String("string"),
				ContainerMetricsConfig: &sagemaker.InferenceComponentSpecificationContainerContainerMetricsConfigArgs{
					MetricsEndpoint: &sagemaker.InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs{
						MetricsEndpointPath:             pulumi.String("string"),
						MetricPublishFrequencyInSeconds: pulumi.Int(0),
					},
				},
				Environment: pulumi.StringMap{
					"string": pulumi.String("string"),
				},
				Image:         pulumi.String("string"),
				ResolvedImage: pulumi.String("string"),
			},
			DataCacheConfig: &sagemaker.InferenceComponentSpecificationDataCacheConfigArgs{
				EnableCaching: pulumi.Bool(false),
			},
			InstanceType: pulumi.String("string"),
			ModelName:    pulumi.String("string"),
			SchedulingConfig: &sagemaker.InferenceComponentSpecificationSchedulingConfigArgs{
				PlacementStrategy: pulumi.String("string"),
				AvailabilityZoneBalance: &sagemaker.InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs{
					EnforcementMode: pulumi.String("string"),
					MaxImbalance:    pulumi.Int(0),
				},
			},
			StartupParameters: &sagemaker.InferenceComponentSpecificationStartupParametersArgs{
				ContainerStartupHealthCheckTimeoutInSeconds: pulumi.Int(0),
				ModelDataDownloadTimeoutInSeconds:           pulumi.Int(0),
			},
		},
	},
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	Timeouts: &sagemaker.InferenceComponentTimeoutsArgs{
		Create: pulumi.String("string"),
		Delete: pulumi.String("string"),
		Update: pulumi.String("string"),
	},
	VariantName: pulumi.String("string"),
})

    resource "aws_sagemaker_inference_component" "inferenceComponentResource" {
  lifecycle {
    create_before_destroy = true
  }
  endpoint_name = "string"
  deployment_config = {
    rolling_update_policy = {
      maximum_batch_size = {
        type  = "string"
        value = 0
      }
      wait_interval_in_seconds             = 0
      maximum_execution_timeout_in_seconds = 0
      rollback_maximum_batch_size = {
        type  = "string"
        value = 0
      }
    }
    auto_rollback_configuration = {
      alarms = [{
        alarm_name = "string"
      }]
    }
  }
  name   = "string"
  region = "string"
  runtime_config = {
    copy_count         = 0
    current_copy_count = 0
    desired_copy_count = 0
    placement_statuses = [{
      current_copy_count = 0
      instance_type      = "string"
    }]
  }
  specification = {
    base_inference_component_name = "string"
    compute_resource_requirements = {
      min_memory_required_in_mb              = 0
      max_memory_required_in_mb              = 0
      number_of_accelerator_devices_required = 0
      number_of_cpu_cores_required           = 0
    }
    container = {
      artifact_url = "string"
      container_metrics_config = {
        metrics_endpoint = {
          metrics_endpoint_path               = "string"
          metric_publish_frequency_in_seconds = 0
        }
      }
      environment = {
        "string" = "string"
      }
      image          = "string"
      resolved_image = "string"
    }
    data_cache_config = {
      enable_caching = false
    }
    instance_type = "string"
    model_name    = "string"
    scheduling_config = {
      placement_strategy = "string"
      availability_zone_balance = {
        enforcement_mode = "string"
        max_imbalance    = 0
      }
    }
    startup_parameters = {
      container_startup_health_check_timeout_in_seconds = 0
      model_data_download_timeout_in_seconds            = 0
    }
  }
  specifications {
    base_inference_component_name = "string"
    compute_resource_requirements = {
      min_memory_required_in_mb              = 0
      max_memory_required_in_mb              = 0
      number_of_accelerator_devices_required = 0
      number_of_cpu_cores_required           = 0
    }
    container = {
      artifact_url = "string"
      container_metrics_config = {
        metrics_endpoint = {
          metrics_endpoint_path               = "string"
          metric_publish_frequency_in_seconds = 0
        }
      }
      environment = {
        "string" = "string"
      }
      image          = "string"
      resolved_image = "string"
    }
    data_cache_config = {
      enable_caching = false
    }
    instance_type = "string"
    model_name    = "string"
    scheduling_config = {
      placement_strategy = "string"
      availability_zone_balance = {
        enforcement_mode = "string"
        max_imbalance    = 0
      }
    }
    startup_parameters = {
      container_startup_health_check_timeout_in_seconds = 0
      model_data_download_timeout_in_seconds            = 0
    }
  }
  tags = {
    "string" = "string"
  }
  timeouts = {
    create = "string"
    delete = "string"
    update = "string"
  }
  variant_name = "string"
}

    var inferenceComponentResource = new InferenceComponent("inferenceComponentResource", InferenceComponentArgs.builder()
    .endpointName("string")
    .deploymentConfig(InferenceComponentDeploymentConfigArgs.builder()
        .rollingUpdatePolicy(InferenceComponentDeploymentConfigRollingUpdatePolicyArgs.builder()
            .maximumBatchSize(InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs.builder()
                .type("string")
                .value(0)
                .build())
            .waitIntervalInSeconds(0)
            .maximumExecutionTimeoutInSeconds(0)
            .rollbackMaximumBatchSize(InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs.builder()
                .type("string")
                .value(0)
                .build())
            .build())
        .autoRollbackConfiguration(InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs.builder()
            .alarms(InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs.builder()
                .alarmName("string")
                .build())
            .build())
        .build())
    .name("string")
    .region("string")
    .runtimeConfig(InferenceComponentRuntimeConfigArgs.builder()
        .copyCount(0)
        .currentCopyCount(0)
        .desiredCopyCount(0)
        .placementStatuses(InferenceComponentRuntimeConfigPlacementStatusArgs.builder()
            .currentCopyCount(0)
            .instanceType("string")
            .build())
        .build())
    .specification(InferenceComponentSpecificationArgs.builder()
        .baseInferenceComponentName("string")
        .computeResourceRequirements(InferenceComponentSpecificationComputeResourceRequirementsArgs.builder()
            .minMemoryRequiredInMb(0)
            .maxMemoryRequiredInMb(0)
            .numberOfAcceleratorDevicesRequired(0.0)
            .numberOfCpuCoresRequired(0.0)
            .build())
        .container(InferenceComponentSpecificationContainerArgs.builder()
            .artifactUrl("string")
            .containerMetricsConfig(InferenceComponentSpecificationContainerContainerMetricsConfigArgs.builder()
                .metricsEndpoint(InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs.builder()
                    .metricsEndpointPath("string")
                    .metricPublishFrequencyInSeconds(0)
                    .build())
                .build())
            .environment(Map.of("string", "string"))
            .image("string")
            .resolvedImage("string")
            .build())
        .dataCacheConfig(InferenceComponentSpecificationDataCacheConfigArgs.builder()
            .enableCaching(false)
            .build())
        .instanceType("string")
        .modelName("string")
        .schedulingConfig(InferenceComponentSpecificationSchedulingConfigArgs.builder()
            .placementStrategy("string")
            .availabilityZoneBalance(InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs.builder()
                .enforcementMode("string")
                .maxImbalance(0)
                .build())
            .build())
        .startupParameters(InferenceComponentSpecificationStartupParametersArgs.builder()
            .containerStartupHealthCheckTimeoutInSeconds(0)
            .modelDataDownloadTimeoutInSeconds(0)
            .build())
        .build())
    .specifications(InferenceComponentSpecificationArgs.builder()
        .baseInferenceComponentName("string")
        .computeResourceRequirements(InferenceComponentSpecificationComputeResourceRequirementsArgs.builder()
            .minMemoryRequiredInMb(0)
            .maxMemoryRequiredInMb(0)
            .numberOfAcceleratorDevicesRequired(0.0)
            .numberOfCpuCoresRequired(0.0)
            .build())
        .container(InferenceComponentSpecificationContainerArgs.builder()
            .artifactUrl("string")
            .containerMetricsConfig(InferenceComponentSpecificationContainerContainerMetricsConfigArgs.builder()
                .metricsEndpoint(InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs.builder()
                    .metricsEndpointPath("string")
                    .metricPublishFrequencyInSeconds(0)
                    .build())
                .build())
            .environment(Map.of("string", "string"))
            .image("string")
            .resolvedImage("string")
            .build())
        .dataCacheConfig(InferenceComponentSpecificationDataCacheConfigArgs.builder()
            .enableCaching(false)
            .build())
        .instanceType("string")
        .modelName("string")
        .schedulingConfig(InferenceComponentSpecificationSchedulingConfigArgs.builder()
            .placementStrategy("string")
            .availabilityZoneBalance(InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs.builder()
                .enforcementMode("string")
                .maxImbalance(0)
                .build())
            .build())
        .startupParameters(InferenceComponentSpecificationStartupParametersArgs.builder()
            .containerStartupHealthCheckTimeoutInSeconds(0)
            .modelDataDownloadTimeoutInSeconds(0)
            .build())
        .build())
    .tags(Map.of("string", "string"))
    .timeouts(InferenceComponentTimeoutsArgs.builder()
        .create("string")
        .delete("string")
        .update("string")
        .build())
    .variantName("string")
    .build());

    inference_component_resource = aws.sagemaker.InferenceComponent("inferenceComponentResource",
    endpoint_name="string",
    deployment_config={
        "rolling_update_policy": {
            "maximum_batch_size": {
                "type": "string",
                "value": 0,
            },
            "wait_interval_in_seconds": 0,
            "maximum_execution_timeout_in_seconds": 0,
            "rollback_maximum_batch_size": {
                "type": "string",
                "value": 0,
            },
        },
        "auto_rollback_configuration": {
            "alarms": [{
                "alarm_name": "string",
            }],
        },
    },
    name="string",
    region="string",
    runtime_config={
        "copy_count": 0,
        "current_copy_count": 0,
        "desired_copy_count": 0,
        "placement_statuses": [{
            "current_copy_count": 0,
            "instance_type": "string",
        }],
    },
    specification={
        "base_inference_component_name": "string",
        "compute_resource_requirements": {
            "min_memory_required_in_mb": 0,
            "max_memory_required_in_mb": 0,
            "number_of_accelerator_devices_required": float(0),
            "number_of_cpu_cores_required": float(0),
        },
        "container": {
            "artifact_url": "string",
            "container_metrics_config": {
                "metrics_endpoint": {
                    "metrics_endpoint_path": "string",
                    "metric_publish_frequency_in_seconds": 0,
                },
            },
            "environment": {
                "string": "string",
            },
            "image": "string",
            "resolved_image": "string",
        },
        "data_cache_config": {
            "enable_caching": False,
        },
        "instance_type": "string",
        "model_name": "string",
        "scheduling_config": {
            "placement_strategy": "string",
            "availability_zone_balance": {
                "enforcement_mode": "string",
                "max_imbalance": 0,
            },
        },
        "startup_parameters": {
            "container_startup_health_check_timeout_in_seconds": 0,
            "model_data_download_timeout_in_seconds": 0,
        },
    },
    specifications=[{
        "base_inference_component_name": "string",
        "compute_resource_requirements": {
            "min_memory_required_in_mb": 0,
            "max_memory_required_in_mb": 0,
            "number_of_accelerator_devices_required": float(0),
            "number_of_cpu_cores_required": float(0),
        },
        "container": {
            "artifact_url": "string",
            "container_metrics_config": {
                "metrics_endpoint": {
                    "metrics_endpoint_path": "string",
                    "metric_publish_frequency_in_seconds": 0,
                },
            },
            "environment": {
                "string": "string",
            },
            "image": "string",
            "resolved_image": "string",
        },
        "data_cache_config": {
            "enable_caching": False,
        },
        "instance_type": "string",
        "model_name": "string",
        "scheduling_config": {
            "placement_strategy": "string",
            "availability_zone_balance": {
                "enforcement_mode": "string",
                "max_imbalance": 0,
            },
        },
        "startup_parameters": {
            "container_startup_health_check_timeout_in_seconds": 0,
            "model_data_download_timeout_in_seconds": 0,
        },
    }],
    tags={
        "string": "string",
    },
    timeouts={
        "create": "string",
        "delete": "string",
        "update": "string",
    },
    variant_name="string")

    const inferenceComponentResource = new aws.sagemaker.InferenceComponent("inferenceComponentResource", {
    endpointName: "string",
    deploymentConfig: {
        rollingUpdatePolicy: {
            maximumBatchSize: {
                type: "string",
                value: 0,
            },
            waitIntervalInSeconds: 0,
            maximumExecutionTimeoutInSeconds: 0,
            rollbackMaximumBatchSize: {
                type: "string",
                value: 0,
            },
        },
        autoRollbackConfiguration: {
            alarms: [{
                alarmName: "string",
            }],
        },
    },
    name: "string",
    region: "string",
    runtimeConfig: {
        copyCount: 0,
        currentCopyCount: 0,
        desiredCopyCount: 0,
        placementStatuses: [{
            currentCopyCount: 0,
            instanceType: "string",
        }],
    },
    specification: {
        baseInferenceComponentName: "string",
        computeResourceRequirements: {
            minMemoryRequiredInMb: 0,
            maxMemoryRequiredInMb: 0,
            numberOfAcceleratorDevicesRequired: 0,
            numberOfCpuCoresRequired: 0,
        },
        container: {
            artifactUrl: "string",
            containerMetricsConfig: {
                metricsEndpoint: {
                    metricsEndpointPath: "string",
                    metricPublishFrequencyInSeconds: 0,
                },
            },
            environment: {
                string: "string",
            },
            image: "string",
            resolvedImage: "string",
        },
        dataCacheConfig: {
            enableCaching: false,
        },
        instanceType: "string",
        modelName: "string",
        schedulingConfig: {
            placementStrategy: "string",
            availabilityZoneBalance: {
                enforcementMode: "string",
                maxImbalance: 0,
            },
        },
        startupParameters: {
            containerStartupHealthCheckTimeoutInSeconds: 0,
            modelDataDownloadTimeoutInSeconds: 0,
        },
    },
    specifications: [{
        baseInferenceComponentName: "string",
        computeResourceRequirements: {
            minMemoryRequiredInMb: 0,
            maxMemoryRequiredInMb: 0,
            numberOfAcceleratorDevicesRequired: 0,
            numberOfCpuCoresRequired: 0,
        },
        container: {
            artifactUrl: "string",
            containerMetricsConfig: {
                metricsEndpoint: {
                    metricsEndpointPath: "string",
                    metricPublishFrequencyInSeconds: 0,
                },
            },
            environment: {
                string: "string",
            },
            image: "string",
            resolvedImage: "string",
        },
        dataCacheConfig: {
            enableCaching: false,
        },
        instanceType: "string",
        modelName: "string",
        schedulingConfig: {
            placementStrategy: "string",
            availabilityZoneBalance: {
                enforcementMode: "string",
                maxImbalance: 0,
            },
        },
        startupParameters: {
            containerStartupHealthCheckTimeoutInSeconds: 0,
            modelDataDownloadTimeoutInSeconds: 0,
        },
    }],
    tags: {
        string: "string",
    },
    timeouts: {
        create: "string",
        "delete": "string",
        update: "string",
    },
    variantName: "string",
});

    type: aws:sagemaker:InferenceComponent
properties:
    deploymentConfig:
        autoRollbackConfiguration:
            alarms:
                - alarmName: string
        rollingUpdatePolicy:
            maximumBatchSize:
                type: string
                value: 0
            maximumExecutionTimeoutInSeconds: 0
            rollbackMaximumBatchSize:
                type: string
                value: 0
            waitIntervalInSeconds: 0
    endpointName: string
    name: string
    region: string
    runtimeConfig:
        copyCount: 0
        currentCopyCount: 0
        desiredCopyCount: 0
        placementStatuses:
            - currentCopyCount: 0
              instanceType: string
    specification:
        baseInferenceComponentName: string
        computeResourceRequirements:
            maxMemoryRequiredInMb: 0
            minMemoryRequiredInMb: 0
            numberOfAcceleratorDevicesRequired: 0
            numberOfCpuCoresRequired: 0
        container:
            artifactUrl: string
            containerMetricsConfig:
                metricsEndpoint:
                    metricPublishFrequencyInSeconds: 0
                    metricsEndpointPath: string
            environment:
                string: string
            image: string
            resolvedImage: string
        dataCacheConfig:
            enableCaching: false
        instanceType: string
        modelName: string
        schedulingConfig:
            availabilityZoneBalance:
                enforcementMode: string
                maxImbalance: 0
            placementStrategy: string
        startupParameters:
            containerStartupHealthCheckTimeoutInSeconds: 0
            modelDataDownloadTimeoutInSeconds: 0
    specifications:
        - baseInferenceComponentName: string
          computeResourceRequirements:
            maxMemoryRequiredInMb: 0
            minMemoryRequiredInMb: 0
            numberOfAcceleratorDevicesRequired: 0
            numberOfCpuCoresRequired: 0
          container:
            artifactUrl: string
            containerMetricsConfig:
                metricsEndpoint:
                    metricPublishFrequencyInSeconds: 0
                    metricsEndpointPath: string
            environment:
                string: string
            image: string
            resolvedImage: string
          dataCacheConfig:
            enableCaching: false
          instanceType: string
          modelName: string
          schedulingConfig:
            availabilityZoneBalance:
                enforcementMode: string
                maxImbalance: 0
            placementStrategy: string
          startupParameters:
            containerStartupHealthCheckTimeoutInSeconds: 0
            modelDataDownloadTimeoutInSeconds: 0
    tags:
        string: string
    timeouts:
        create: string
        delete: string
        update: string
    variantName: string

    InferenceComponent Resource Properties

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

    Inputs

    In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

    The InferenceComponent resource accepts the following input properties:

    EndpointName string
    Name of an existing endpoint where you host the inference component.
    DeploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    Name string
    Unique name to assign to the inference component.
    Region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    RuntimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    Specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Specifications List<InferenceComponentSpecification>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Tags Dictionary<string, string>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    Timeouts InferenceComponentTimeouts
    VariantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    EndpointName string
    Name of an existing endpoint where you host the inference component.
    DeploymentConfig InferenceComponentDeploymentConfigArgs
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    Name string
    Unique name to assign to the inference component.
    Region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    RuntimeConfig InferenceComponentRuntimeConfigArgs
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    Specification InferenceComponentSpecificationArgs
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Specifications []InferenceComponentSpecificationArgs
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Tags map[string]string
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    Timeouts InferenceComponentTimeoutsArgs
    VariantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    endpoint_name string
    Name of an existing endpoint where you host the inference component.
    deployment_config object
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    name string
    Unique name to assign to the inference component.
    region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtime_config object
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification object
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications list(object)
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    tags map(string)
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeouts object
    variant_name string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    endpointName String
    Name of an existing endpoint where you host the inference component.
    deploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    name String
    Unique name to assign to the inference component.
    region String
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications List<InferenceComponentSpecification>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    tags Map<String,String>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeouts InferenceComponentTimeouts
    variantName String
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    endpointName string
    Name of an existing endpoint where you host the inference component.
    deploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    name string
    Unique name to assign to the inference component.
    region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications InferenceComponentSpecification[]
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    tags {[key: string]: string}
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeouts InferenceComponentTimeouts
    variantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    endpoint_name str
    Name of an existing endpoint where you host the inference component.
    deployment_config InferenceComponentDeploymentConfigArgs
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    name str
    Unique name to assign to the inference component.
    region str
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtime_config InferenceComponentRuntimeConfigArgs
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecificationArgs
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications Sequence[InferenceComponentSpecificationArgs]
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    tags Mapping[str, str]
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeouts InferenceComponentTimeoutsArgs
    variant_name str
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    endpointName String
    Name of an existing endpoint where you host the inference component.
    deploymentConfig Property Map
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    name String
    Unique name to assign to the inference component.
    region String
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig Property Map
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification Property Map
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications List<Property Map>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    tags Map<String>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    timeouts Property Map
    variantName String
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).

    Outputs

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

    Arn string
    ARN of the inference component.
    CreationTime string
    Time when the inference component was created.
    EndpointArn string
    ARN of the endpoint that hosts the inference component.
    FailureReason string
    If the inference component status is Failed, the reason for the failure.
    Id string
    The provider-assigned unique ID for this managed resource.
    LastModifiedTime string
    Time when the inference component was last updated.
    Status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    TagsAll Dictionary<string, string>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    Arn string
    ARN of the inference component.
    CreationTime string
    Time when the inference component was created.
    EndpointArn string
    ARN of the endpoint that hosts the inference component.
    FailureReason string
    If the inference component status is Failed, the reason for the failure.
    Id string
    The provider-assigned unique ID for this managed resource.
    LastModifiedTime string
    Time when the inference component was last updated.
    Status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    TagsAll map[string]string
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    arn string
    ARN of the inference component.
    creation_time string
    Time when the inference component was created.
    endpoint_arn string
    ARN of the endpoint that hosts the inference component.
    failure_reason string
    If the inference component status is Failed, the reason for the failure.
    id string
    The provider-assigned unique ID for this managed resource.
    last_modified_time string
    Time when the inference component was last updated.
    status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags_all map(string)
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    arn String
    ARN of the inference component.
    creationTime String
    Time when the inference component was created.
    endpointArn String
    ARN of the endpoint that hosts the inference component.
    failureReason String
    If the inference component status is Failed, the reason for the failure.
    id String
    The provider-assigned unique ID for this managed resource.
    lastModifiedTime String
    Time when the inference component was last updated.
    status String
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tagsAll Map<String,String>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    arn string
    ARN of the inference component.
    creationTime string
    Time when the inference component was created.
    endpointArn string
    ARN of the endpoint that hosts the inference component.
    failureReason string
    If the inference component status is Failed, the reason for the failure.
    id string
    The provider-assigned unique ID for this managed resource.
    lastModifiedTime string
    Time when the inference component was last updated.
    status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tagsAll {[key: string]: string}
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    arn str
    ARN of the inference component.
    creation_time str
    Time when the inference component was created.
    endpoint_arn str
    ARN of the endpoint that hosts the inference component.
    failure_reason str
    If the inference component status is Failed, the reason for the failure.
    id str
    The provider-assigned unique ID for this managed resource.
    last_modified_time str
    Time when the inference component was last updated.
    status str
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags_all Mapping[str, str]
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    arn String
    ARN of the inference component.
    creationTime String
    Time when the inference component was created.
    endpointArn String
    ARN of the endpoint that hosts the inference component.
    failureReason String
    If the inference component status is Failed, the reason for the failure.
    id String
    The provider-assigned unique ID for this managed resource.
    lastModifiedTime String
    Time when the inference component was last updated.
    status String
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tagsAll Map<String>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.

    Look up Existing InferenceComponent Resource

    Get an existing InferenceComponent 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?: InferenceComponentState, opts?: CustomResourceOptions): InferenceComponent
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        creation_time: Optional[str] = None,
        deployment_config: Optional[InferenceComponentDeploymentConfigArgs] = None,
        endpoint_arn: Optional[str] = None,
        endpoint_name: Optional[str] = None,
        failure_reason: Optional[str] = None,
        last_modified_time: Optional[str] = None,
        name: Optional[str] = None,
        region: Optional[str] = None,
        runtime_config: Optional[InferenceComponentRuntimeConfigArgs] = None,
        specification: Optional[InferenceComponentSpecificationArgs] = None,
        specifications: Optional[Sequence[InferenceComponentSpecificationArgs]] = None,
        status: Optional[str] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None,
        timeouts: Optional[InferenceComponentTimeoutsArgs] = None,
        variant_name: Optional[str] = None) -> InferenceComponent
    func GetInferenceComponent(ctx *Context, name string, id IDInput, state *InferenceComponentState, opts ...ResourceOption) (*InferenceComponent, error)
    public static InferenceComponent Get(string name, Input<string> id, InferenceComponentState? state, CustomResourceOptions? opts = null)
    public static InferenceComponent get(String name, Output<String> id, InferenceComponentState state, CustomResourceOptions options)
    resources:  _:    type: aws:sagemaker:InferenceComponent    get:      id: ${id}
    import {
  to = aws_sagemaker_inference_component.example
  id = "${id}"
}
    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
    ARN of the inference component.
    CreationTime string
    Time when the inference component was created.
    DeploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    EndpointArn string
    ARN of the endpoint that hosts the inference component.
    EndpointName string
    Name of an existing endpoint where you host the inference component.
    FailureReason string
    If the inference component status is Failed, the reason for the failure.
    LastModifiedTime string
    Time when the inference component was last updated.
    Name string
    Unique name to assign to the inference component.
    Region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    RuntimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    Specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Specifications List<InferenceComponentSpecification>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    Tags Dictionary<string, string>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    TagsAll Dictionary<string, string>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    Timeouts InferenceComponentTimeouts
    VariantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    Arn string
    ARN of the inference component.
    CreationTime string
    Time when the inference component was created.
    DeploymentConfig InferenceComponentDeploymentConfigArgs
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    EndpointArn string
    ARN of the endpoint that hosts the inference component.
    EndpointName string
    Name of an existing endpoint where you host the inference component.
    FailureReason string
    If the inference component status is Failed, the reason for the failure.
    LastModifiedTime string
    Time when the inference component was last updated.
    Name string
    Unique name to assign to the inference component.
    Region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    RuntimeConfig InferenceComponentRuntimeConfigArgs
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    Specification InferenceComponentSpecificationArgs
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Specifications []InferenceComponentSpecificationArgs
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    Status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    Tags map[string]string
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    TagsAll map[string]string
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    Timeouts InferenceComponentTimeoutsArgs
    VariantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    arn string
    ARN of the inference component.
    creation_time string
    Time when the inference component was created.
    deployment_config object
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    endpoint_arn string
    ARN of the endpoint that hosts the inference component.
    endpoint_name string
    Name of an existing endpoint where you host the inference component.
    failure_reason string
    If the inference component status is Failed, the reason for the failure.
    last_modified_time string
    Time when the inference component was last updated.
    name string
    Unique name to assign to the inference component.
    region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtime_config object
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification object
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications list(object)
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags map(string)
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    tags_all map(string)
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    timeouts object
    variant_name string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    arn String
    ARN of the inference component.
    creationTime String
    Time when the inference component was created.
    deploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    endpointArn String
    ARN of the endpoint that hosts the inference component.
    endpointName String
    Name of an existing endpoint where you host the inference component.
    failureReason String
    If the inference component status is Failed, the reason for the failure.
    lastModifiedTime String
    Time when the inference component was last updated.
    name String
    Unique name to assign to the inference component.
    region String
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications List<InferenceComponentSpecification>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    status String
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags Map<String,String>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll Map<String,String>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    timeouts InferenceComponentTimeouts
    variantName String
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    arn string
    ARN of the inference component.
    creationTime string
    Time when the inference component was created.
    deploymentConfig InferenceComponentDeploymentConfig
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    endpointArn string
    ARN of the endpoint that hosts the inference component.
    endpointName string
    Name of an existing endpoint where you host the inference component.
    failureReason string
    If the inference component status is Failed, the reason for the failure.
    lastModifiedTime string
    Time when the inference component was last updated.
    name string
    Unique name to assign to the inference component.
    region string
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig InferenceComponentRuntimeConfig
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecification
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications InferenceComponentSpecification[]
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    status string
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags {[key: string]: string}
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll {[key: string]: string}
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    timeouts InferenceComponentTimeouts
    variantName string
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    arn str
    ARN of the inference component.
    creation_time str
    Time when the inference component was created.
    deployment_config InferenceComponentDeploymentConfigArgs
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    endpoint_arn str
    ARN of the endpoint that hosts the inference component.
    endpoint_name str
    Name of an existing endpoint where you host the inference component.
    failure_reason str
    If the inference component status is Failed, the reason for the failure.
    last_modified_time str
    Time when the inference component was last updated.
    name str
    Unique name to assign to the inference component.
    region str
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtime_config InferenceComponentRuntimeConfigArgs
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification InferenceComponentSpecificationArgs
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications Sequence[InferenceComponentSpecificationArgs]
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    status str
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags Mapping[str, str]
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    tags_all Mapping[str, str]
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    timeouts InferenceComponentTimeoutsArgs
    variant_name str
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).
    arn String
    ARN of the inference component.
    creationTime String
    Time when the inference component was created.
    deploymentConfig Property Map
    Deployment configuration for the inference component, which controls the rollout strategy and rollback behavior. This directive applies only when the inference component is updated — the CreateInferenceComponent API does not accept it, so it has no effect on initial creation. It is not returned by the API and is therefore not refreshed into state or verified on import. See deploymentConfig Block.
    endpointArn String
    ARN of the endpoint that hosts the inference component.
    endpointName String
    Name of an existing endpoint where you host the inference component.
    failureReason String
    If the inference component status is Failed, the reason for the failure.
    lastModifiedTime String
    Time when the inference component was last updated.
    name String
    Unique name to assign to the inference component.
    region String
    Region where this resource will be managed. Defaults to the Region set in the provider configuration.
    runtimeConfig Property Map
    Runtime settings for a model that is deployed with an inference component. See runtimeConfig Block.
    specification Property Map
    Details about the resources to deploy with this inference component. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    specifications List<Property Map>
    List of specification objects for the inference component, one per instance type. At least two blocks are required; configure specification instead to deploy to a single instance type. Exactly one of specification or specifications must be configured. See specification and specifications Block.
    status String
    Status of the inference component (e.g., InService, Creating, Updating, Failed, Deleting).
    tags Map<String>
    Map of tags to assign to the resource. If configured with a provider defaultTags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll Map<String>
    Map of tags assigned to the resource, including those inherited from the provider defaultTags configuration block.
    timeouts Property Map
    variantName String
    Name of an existing production variant where you host the inference component. Required for a standard inference component; must be omitted for an adapter inference component (one that sets baseInferenceComponentName).

    Supporting Types

    InferenceComponentDeploymentConfig, InferenceComponentDeploymentConfigArgs

    RollingUpdatePolicy InferenceComponentDeploymentConfigRollingUpdatePolicy
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    AutoRollbackConfiguration InferenceComponentDeploymentConfigAutoRollbackConfiguration
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    RollingUpdatePolicy InferenceComponentDeploymentConfigRollingUpdatePolicy
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    AutoRollbackConfiguration InferenceComponentDeploymentConfigAutoRollbackConfiguration
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    rolling_update_policy object
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    auto_rollback_configuration object
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    rollingUpdatePolicy InferenceComponentDeploymentConfigRollingUpdatePolicy
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    autoRollbackConfiguration InferenceComponentDeploymentConfigAutoRollbackConfiguration
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    rollingUpdatePolicy InferenceComponentDeploymentConfigRollingUpdatePolicy
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    autoRollbackConfiguration InferenceComponentDeploymentConfigAutoRollbackConfiguration
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    rolling_update_policy InferenceComponentDeploymentConfigRollingUpdatePolicy
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    auto_rollback_configuration InferenceComponentDeploymentConfigAutoRollbackConfiguration
    Automatic rollback configuration. See autoRollbackConfiguration Block.
    rollingUpdatePolicy Property Map
    Rolling deployment strategy. See rollingUpdatePolicy Block.
    autoRollbackConfiguration Property Map
    Automatic rollback configuration. See autoRollbackConfiguration Block.

    InferenceComponentDeploymentConfigAutoRollbackConfiguration, InferenceComponentDeploymentConfigAutoRollbackConfigurationArgs

    Alarms List<InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm>
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    Alarms []InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    alarms list(object)
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    alarms List<InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm>
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    alarms InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm[]
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    alarms Sequence[InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm]
    List of CloudWatch alarms that trigger rollback. See alarms Block.
    alarms List<Property Map>
    List of CloudWatch alarms that trigger rollback. See alarms Block.

    InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarm, InferenceComponentDeploymentConfigAutoRollbackConfigurationAlarmArgs

    AlarmName string
    Name of a CloudWatch alarm.
    AlarmName string
    Name of a CloudWatch alarm.
    alarm_name string
    Name of a CloudWatch alarm.
    alarmName String
    Name of a CloudWatch alarm.
    alarmName string
    Name of a CloudWatch alarm.
    alarm_name str
    Name of a CloudWatch alarm.
    alarmName String
    Name of a CloudWatch alarm.

    InferenceComponentDeploymentConfigRollingUpdatePolicy, InferenceComponentDeploymentConfigRollingUpdatePolicyArgs

    MaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    WaitIntervalInSeconds int
    Length of the baking period in seconds. Valid values: 0-3600.
    MaximumExecutionTimeoutInSeconds int
    Time limit for the total deployment. Valid values are between 600 and 28800.
    RollbackMaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    MaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    WaitIntervalInSeconds int
    Length of the baking period in seconds. Valid values: 0-3600.
    MaximumExecutionTimeoutInSeconds int
    Time limit for the total deployment. Valid values are between 600 and 28800.
    RollbackMaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    maximum_batch_size object
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    wait_interval_in_seconds number
    Length of the baking period in seconds. Valid values: 0-3600.
    maximum_execution_timeout_in_seconds number
    Time limit for the total deployment. Valid values are between 600 and 28800.
    rollback_maximum_batch_size object
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    maximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    waitIntervalInSeconds Integer
    Length of the baking period in seconds. Valid values: 0-3600.
    maximumExecutionTimeoutInSeconds Integer
    Time limit for the total deployment. Valid values are between 600 and 28800.
    rollbackMaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    maximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    waitIntervalInSeconds number
    Length of the baking period in seconds. Valid values: 0-3600.
    maximumExecutionTimeoutInSeconds number
    Time limit for the total deployment. Valid values are between 600 and 28800.
    rollbackMaximumBatchSize InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    maximum_batch_size InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    wait_interval_in_seconds int
    Length of the baking period in seconds. Valid values: 0-3600.
    maximum_execution_timeout_in_seconds int
    Time limit for the total deployment. Valid values are between 600 and 28800.
    rollback_maximum_batch_size InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.
    maximumBatchSize Property Map
    Batch size for each rolling step. See maximumBatchSize and rollbackMaximumBatchSize Block.
    waitIntervalInSeconds Number
    Length of the baking period in seconds. Valid values: 0-3600.
    maximumExecutionTimeoutInSeconds Number
    Time limit for the total deployment. Valid values are between 600 and 28800.
    rollbackMaximumBatchSize Property Map
    Batch size for a rollback. See maximumBatchSize and rollbackMaximumBatchSize Block.

    InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSize, InferenceComponentDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs

    Type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    Value int
    Capacity size value.
    Type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    Value int
    Capacity size value.
    type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value number
    Capacity size value.
    type String
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value Integer
    Capacity size value.
    type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value number
    Capacity size value.
    type str
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value int
    Capacity size value.
    type String
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value Number
    Capacity size value.

    InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize, InferenceComponentDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs

    Type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    Value int
    Capacity size value.
    Type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    Value int
    Capacity size value.
    type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value number
    Capacity size value.
    type String
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value Integer
    Capacity size value.
    type string
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value number
    Capacity size value.
    type str
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value int
    Capacity size value.
    type String
    Capacity size type. Valid values: COPY_COUNT, CAPACITY_PERCENT.
    value Number
    Capacity size value.

    InferenceComponentRuntimeConfig, InferenceComponentRuntimeConfigArgs

    CopyCount int
    Number of runtime copies of the model container to deploy.
    CurrentCopyCount int
    Number of copies placed on this instance type.
    DesiredCopyCount int
    Number of runtime copies requested.
    PlacementStatuses List<InferenceComponentRuntimeConfigPlacementStatus>
    Placement status of the inference component copies across instance types. See below.
    CopyCount int
    Number of runtime copies of the model container to deploy.
    CurrentCopyCount int
    Number of copies placed on this instance type.
    DesiredCopyCount int
    Number of runtime copies requested.
    PlacementStatuses []InferenceComponentRuntimeConfigPlacementStatus
    Placement status of the inference component copies across instance types. See below.
    copy_count number
    Number of runtime copies of the model container to deploy.
    current_copy_count number
    Number of copies placed on this instance type.
    desired_copy_count number
    Number of runtime copies requested.
    placement_statuses list(object)
    Placement status of the inference component copies across instance types. See below.
    copyCount Integer
    Number of runtime copies of the model container to deploy.
    currentCopyCount Integer
    Number of copies placed on this instance type.
    desiredCopyCount Integer
    Number of runtime copies requested.
    placementStatuses List<InferenceComponentRuntimeConfigPlacementStatus>
    Placement status of the inference component copies across instance types. See below.
    copyCount number
    Number of runtime copies of the model container to deploy.
    currentCopyCount number
    Number of copies placed on this instance type.
    desiredCopyCount number
    Number of runtime copies requested.
    placementStatuses InferenceComponentRuntimeConfigPlacementStatus[]
    Placement status of the inference component copies across instance types. See below.
    copy_count int
    Number of runtime copies of the model container to deploy.
    current_copy_count int
    Number of copies placed on this instance type.
    desired_copy_count int
    Number of runtime copies requested.
    placement_statuses Sequence[InferenceComponentRuntimeConfigPlacementStatus]
    Placement status of the inference component copies across instance types. See below.
    copyCount Number
    Number of runtime copies of the model container to deploy.
    currentCopyCount Number
    Number of copies placed on this instance type.
    desiredCopyCount Number
    Number of runtime copies requested.
    placementStatuses List<Property Map>
    Placement status of the inference component copies across instance types. See below.

    InferenceComponentRuntimeConfigPlacementStatus, InferenceComponentRuntimeConfigPlacementStatusArgs

    CurrentCopyCount int
    Number of copies placed on this instance type.
    InstanceType string
    Instance type on which the copies are placed.
    CurrentCopyCount int
    Number of copies placed on this instance type.
    InstanceType string
    Instance type on which the copies are placed.
    current_copy_count number
    Number of copies placed on this instance type.
    instance_type string
    Instance type on which the copies are placed.
    currentCopyCount Integer
    Number of copies placed on this instance type.
    instanceType String
    Instance type on which the copies are placed.
    currentCopyCount number
    Number of copies placed on this instance type.
    instanceType string
    Instance type on which the copies are placed.
    current_copy_count int
    Number of copies placed on this instance type.
    instance_type str
    Instance type on which the copies are placed.
    currentCopyCount Number
    Number of copies placed on this instance type.
    instanceType String
    Instance type on which the copies are placed.

    InferenceComponentSpecification, InferenceComponentSpecificationArgs

    BaseInferenceComponentName string
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    ComputeResourceRequirements InferenceComponentSpecificationComputeResourceRequirements
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    Container InferenceComponentSpecificationContainer
    Container that provides the runtime environment for a model. See container Block.
    DataCacheConfig InferenceComponentSpecificationDataCacheConfig
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    InstanceType string
    Instance type on which the copies are placed.
    ModelName string
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    SchedulingConfig InferenceComponentSpecificationSchedulingConfig
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    StartupParameters InferenceComponentSpecificationStartupParameters
    Settings that take effect while the model container starts up. See startupParameters Block.
    BaseInferenceComponentName string
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    ComputeResourceRequirements InferenceComponentSpecificationComputeResourceRequirements
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    Container InferenceComponentSpecificationContainer
    Container that provides the runtime environment for a model. See container Block.
    DataCacheConfig InferenceComponentSpecificationDataCacheConfig
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    InstanceType string
    Instance type on which the copies are placed.
    ModelName string
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    SchedulingConfig InferenceComponentSpecificationSchedulingConfig
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    StartupParameters InferenceComponentSpecificationStartupParameters
    Settings that take effect while the model container starts up. See startupParameters Block.
    base_inference_component_name string
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    compute_resource_requirements object
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    container object
    Container that provides the runtime environment for a model. See container Block.
    data_cache_config object
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    instance_type string
    Instance type on which the copies are placed.
    model_name string
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    scheduling_config object
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    startup_parameters object
    Settings that take effect while the model container starts up. See startupParameters Block.
    baseInferenceComponentName String
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    computeResourceRequirements InferenceComponentSpecificationComputeResourceRequirements
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    container InferenceComponentSpecificationContainer
    Container that provides the runtime environment for a model. See container Block.
    dataCacheConfig InferenceComponentSpecificationDataCacheConfig
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    instanceType String
    Instance type on which the copies are placed.
    modelName String
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    schedulingConfig InferenceComponentSpecificationSchedulingConfig
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    startupParameters InferenceComponentSpecificationStartupParameters
    Settings that take effect while the model container starts up. See startupParameters Block.
    baseInferenceComponentName string
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    computeResourceRequirements InferenceComponentSpecificationComputeResourceRequirements
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    container InferenceComponentSpecificationContainer
    Container that provides the runtime environment for a model. See container Block.
    dataCacheConfig InferenceComponentSpecificationDataCacheConfig
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    instanceType string
    Instance type on which the copies are placed.
    modelName string
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    schedulingConfig InferenceComponentSpecificationSchedulingConfig
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    startupParameters InferenceComponentSpecificationStartupParameters
    Settings that take effect while the model container starts up. See startupParameters Block.
    base_inference_component_name str
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    compute_resource_requirements InferenceComponentSpecificationComputeResourceRequirements
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    container InferenceComponentSpecificationContainer
    Container that provides the runtime environment for a model. See container Block.
    data_cache_config InferenceComponentSpecificationDataCacheConfig
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    instance_type str
    Instance type on which the copies are placed.
    model_name str
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    scheduling_config InferenceComponentSpecificationSchedulingConfig
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    startup_parameters InferenceComponentSpecificationStartupParameters
    Settings that take effect while the model container starts up. See startupParameters Block.
    baseInferenceComponentName String
    Name of an existing inference component that is to contain the inference component that you're creating. Used for adapter inference components.
    computeResourceRequirements Property Map
    Compute resources allocated to run a model. See computeResourceRequirements Block.
    container Property Map
    Container that provides the runtime environment for a model. See container Block.
    dataCacheConfig Property Map
    Settings that affect how the inference component caches data. See dataCacheConfig Block.
    instanceType String
    Instance type on which the copies are placed.
    modelName String
    Name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    schedulingConfig Property Map
    Scheduling configuration for placing inference component copies. See schedulingConfig Block.
    startupParameters Property Map
    Settings that take effect while the model container starts up. See startupParameters Block.

    InferenceComponentSpecificationComputeResourceRequirements, InferenceComponentSpecificationComputeResourceRequirementsArgs

    MinMemoryRequiredInMb int
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    MaxMemoryRequiredInMb int
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    NumberOfAcceleratorDevicesRequired double
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    NumberOfCpuCoresRequired double
    Number of CPU cores to allocate. Minimum value of 0.25.
    MinMemoryRequiredInMb int
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    MaxMemoryRequiredInMb int
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    NumberOfAcceleratorDevicesRequired float64
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    NumberOfCpuCoresRequired float64
    Number of CPU cores to allocate. Minimum value of 0.25.
    min_memory_required_in_mb number
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    max_memory_required_in_mb number
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    number_of_accelerator_devices_required number
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    number_of_cpu_cores_required number
    Number of CPU cores to allocate. Minimum value of 0.25.
    minMemoryRequiredInMb Integer
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    maxMemoryRequiredInMb Integer
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    numberOfAcceleratorDevicesRequired Double
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    numberOfCpuCoresRequired Double
    Number of CPU cores to allocate. Minimum value of 0.25.
    minMemoryRequiredInMb number
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    maxMemoryRequiredInMb number
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    numberOfAcceleratorDevicesRequired number
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    numberOfCpuCoresRequired number
    Number of CPU cores to allocate. Minimum value of 0.25.
    min_memory_required_in_mb int
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    max_memory_required_in_mb int
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    number_of_accelerator_devices_required float
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    number_of_cpu_cores_required float
    Number of CPU cores to allocate. Minimum value of 0.25.
    minMemoryRequiredInMb Number
    Minimum MB of memory to allocate to run a model. Minimum value of 128.
    maxMemoryRequiredInMb Number
    Maximum MB of memory to allocate to run a model. Minimum value of 128.
    numberOfAcceleratorDevicesRequired Number
    Number of accelerators (GPUs or AWS Inferentia) to allocate. Minimum value of 1.
    numberOfCpuCoresRequired Number
    Number of CPU cores to allocate. Minimum value of 0.25.

    InferenceComponentSpecificationContainer, InferenceComponentSpecificationContainerArgs

    ArtifactUrl string
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    ContainerMetricsConfig InferenceComponentSpecificationContainerContainerMetricsConfig
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    Environment Dictionary<string, string>
    Environment variables to set in the Docker container.
    Image string
    Amazon ECR path where the Docker image for the model is stored.
    ResolvedImage string
    Specific digest path of the container image that was resolved and deployed.
    ArtifactUrl string
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    ContainerMetricsConfig InferenceComponentSpecificationContainerContainerMetricsConfig
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    Environment map[string]string
    Environment variables to set in the Docker container.
    Image string
    Amazon ECR path where the Docker image for the model is stored.
    ResolvedImage string
    Specific digest path of the container image that was resolved and deployed.
    artifact_url string
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    container_metrics_config object
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    environment map(string)
    Environment variables to set in the Docker container.
    image string
    Amazon ECR path where the Docker image for the model is stored.
    resolved_image string
    Specific digest path of the container image that was resolved and deployed.
    artifactUrl String
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    containerMetricsConfig InferenceComponentSpecificationContainerContainerMetricsConfig
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    environment Map<String,String>
    Environment variables to set in the Docker container.
    image String
    Amazon ECR path where the Docker image for the model is stored.
    resolvedImage String
    Specific digest path of the container image that was resolved and deployed.
    artifactUrl string
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    containerMetricsConfig InferenceComponentSpecificationContainerContainerMetricsConfig
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    environment {[key: string]: string}
    Environment variables to set in the Docker container.
    image string
    Amazon ECR path where the Docker image for the model is stored.
    resolvedImage string
    Specific digest path of the container image that was resolved and deployed.
    artifact_url str
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    container_metrics_config InferenceComponentSpecificationContainerContainerMetricsConfig
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    environment Mapping[str, str]
    Environment variables to set in the Docker container.
    image str
    Amazon ECR path where the Docker image for the model is stored.
    resolved_image str
    Specific digest path of the container image that was resolved and deployed.
    artifactUrl String
    Amazon S3 path where the model artifacts are stored (.tar.gz).
    containerMetricsConfig Property Map
    Configuration for container metrics scraping. See containerMetricsConfig Block.
    environment Map<String>
    Environment variables to set in the Docker container.
    image String
    Amazon ECR path where the Docker image for the model is stored.
    resolvedImage String
    Specific digest path of the container image that was resolved and deployed.

    InferenceComponentSpecificationContainerContainerMetricsConfig, InferenceComponentSpecificationContainerContainerMetricsConfigArgs

    metrics_endpoint object
    Metrics endpoint configuration. See metricsEndpoint Block.
    metricsEndpoint Property Map
    Metrics endpoint configuration. See metricsEndpoint Block.

    InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpoint, InferenceComponentSpecificationContainerContainerMetricsConfigMetricsEndpointArgs

    MetricsEndpointPath string
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    MetricPublishFrequencyInSeconds int
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    MetricsEndpointPath string
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    MetricPublishFrequencyInSeconds int
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    metrics_endpoint_path string
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    metric_publish_frequency_in_seconds number
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    metricsEndpointPath String
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    metricPublishFrequencyInSeconds Integer
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    metricsEndpointPath string
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    metricPublishFrequencyInSeconds number
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    metrics_endpoint_path str
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    metric_publish_frequency_in_seconds int
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.
    metricsEndpointPath String
    Path to the metrics endpoint. Must start with /. Maximum 256 characters.
    metricPublishFrequencyInSeconds Number
    Interval in seconds at which metrics are published. Valid values: 10, 30, 60, 120, 180, 240, 300. Defaults to 60.

    InferenceComponentSpecificationDataCacheConfig, InferenceComponentSpecificationDataCacheConfigArgs

    EnableCaching bool
    Whether the endpoint caches model artifacts and container images.
    EnableCaching bool
    Whether the endpoint caches model artifacts and container images.
    enable_caching bool
    Whether the endpoint caches model artifacts and container images.
    enableCaching Boolean
    Whether the endpoint caches model artifacts and container images.
    enableCaching boolean
    Whether the endpoint caches model artifacts and container images.
    enable_caching bool
    Whether the endpoint caches model artifacts and container images.
    enableCaching Boolean
    Whether the endpoint caches model artifacts and container images.

    InferenceComponentSpecificationSchedulingConfig, InferenceComponentSpecificationSchedulingConfigArgs

    PlacementStrategy string
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    AvailabilityZoneBalance InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    PlacementStrategy string
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    AvailabilityZoneBalance InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    placement_strategy string
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    availability_zone_balance object
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    placementStrategy String
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    availabilityZoneBalance InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    placementStrategy string
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    availabilityZoneBalance InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    placement_strategy str
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    availability_zone_balance InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.
    placementStrategy String
    Strategy for placing inference component copies. Valid values: SPREAD, BINPACK.
    availabilityZoneBalance Property Map
    Configuration for balancing copies across Availability Zones. See availabilityZoneBalance Block.

    InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalance, InferenceComponentSpecificationSchedulingConfigAvailabilityZoneBalanceArgs

    EnforcementMode string
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    MaxImbalance int
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    EnforcementMode string
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    MaxImbalance int
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    enforcement_mode string
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    max_imbalance number
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    enforcementMode String
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    maxImbalance Integer
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    enforcementMode string
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    maxImbalance number
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    enforcement_mode str
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    max_imbalance int
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.
    enforcementMode String
    How strictly the AZ balance constraint is enforced. Valid values: PERMISSIVE.
    maxImbalance Number
    Maximum allowed difference in copy count between any two Availability Zones. Defaults to 0, which the service applies but does not report, so the value stays absent from state unless configured.

    InferenceComponentSpecificationStartupParameters, InferenceComponentSpecificationStartupParametersArgs

    ContainerStartupHealthCheckTimeoutInSeconds int
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    ModelDataDownloadTimeoutInSeconds int
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    ContainerStartupHealthCheckTimeoutInSeconds int
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    ModelDataDownloadTimeoutInSeconds int
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    container_startup_health_check_timeout_in_seconds number
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    model_data_download_timeout_in_seconds number
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    containerStartupHealthCheckTimeoutInSeconds Integer
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    modelDataDownloadTimeoutInSeconds Integer
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    containerStartupHealthCheckTimeoutInSeconds number
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    modelDataDownloadTimeoutInSeconds number
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    container_startup_health_check_timeout_in_seconds int
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    model_data_download_timeout_in_seconds int
    Timeout in seconds to download and extract the model. Valid values: 60-3600.
    containerStartupHealthCheckTimeoutInSeconds Number
    Timeout in seconds for the inference container to pass health check. Valid values: 60-3600.
    modelDataDownloadTimeoutInSeconds Number
    Timeout in seconds to download and extract the model. Valid values: 60-3600.

    InferenceComponentTimeouts, InferenceComponentTimeoutsArgs

    Create string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    Delete string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    Update string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    Create string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    Delete string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    Update string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    create string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    delete string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    update string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    create String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    delete String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    update String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    create string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    delete string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    update string
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    create str
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    delete str
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    update str
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    create String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
    delete String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
    update String
    A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).

    Import

    Identity Schema

    Required

    • name (String) Name of the inference component.

    Optional

    • accountId (String) AWS Account where this resource is managed.
    • region (String) Region where this resource is managed.

    Using pulumi import, import SageMaker AI Inference Components using the name. For example:

    $ pulumi import aws:sagemaker/inferenceComponent:InferenceComponent example my-inference-component

    To learn more about importing existing cloud resources, see Importing resources.

    Package Details

    Repository
    AWS Classic pulumi/pulumi-aws
    License
    Apache-2.0
    Notes
    This Pulumi package is based on the aws Terraform Provider.
    aws logo aws logo
    Viewing docs for AWS v7.52.1
    published on Wednesday, Oct 28, 2026 by Pulumi
    Schema (JSON)
    pulumi/pulumi-aws

      Try Pulumi Cloud free.
      Your team will thank you.

      Start free trial