Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS Cloud Control
  3. API Docs
  4. sagemaker
  5. InferenceComponent

We recommend new projects start with resources from the AWS provider.

AWS Cloud Control v1.26.0 published on Wednesday, Mar 12, 2025 by Pulumi
pulumi/pulumi-aws-native

aws-native.sagemaker.InferenceComponent

Explore with Pulumi AI

aws-native logo

We recommend new projects start with resources from the AWS provider.

AWS Cloud Control v1.26.0 published on Wednesday, Mar 12, 2025 by Pulumi
pulumi/pulumi-aws-native

    Resource Type definition for AWS::SageMaker::InferenceComponent

    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,
                       specification: Optional[InferenceComponentSpecificationArgs] = None,
                       deployment_config: Optional[InferenceComponentDeploymentConfigArgs] = None,
                       endpoint_arn: Optional[str] = None,
                       inference_component_name: Optional[str] = None,
                       runtime_config: Optional[InferenceComponentRuntimeConfigArgs] = None,
                       tags: Optional[Sequence[_root_inputs.TagArgs]] = 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-native:sagemaker:InferenceComponent
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

    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.

    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
    The name of the endpoint that hosts the inference component.
    Specification Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentSpecification
    DeploymentConfig Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentDeploymentConfig
    EndpointArn string
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    InferenceComponentName string
    The name of the inference component.
    RuntimeConfig Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentRuntimeConfig
    Tags List<Pulumi.AwsNative.Inputs.Tag>
    VariantName string
    The name of the production variant that hosts the inference component.
    EndpointName string
    The name of the endpoint that hosts the inference component.
    Specification InferenceComponentSpecificationArgs
    DeploymentConfig InferenceComponentDeploymentConfigArgs
    EndpointArn string
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    InferenceComponentName string
    The name of the inference component.
    RuntimeConfig InferenceComponentRuntimeConfigArgs
    Tags TagArgs
    VariantName string
    The name of the production variant that hosts the inference component.
    endpointName String
    The name of the endpoint that hosts the inference component.
    specification InferenceComponentSpecification
    deploymentConfig InferenceComponentDeploymentConfig
    endpointArn String
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    inferenceComponentName String
    The name of the inference component.
    runtimeConfig InferenceComponentRuntimeConfig
    tags List<Tag>
    variantName String
    The name of the production variant that hosts the inference component.
    endpointName string
    The name of the endpoint that hosts the inference component.
    specification InferenceComponentSpecification
    deploymentConfig InferenceComponentDeploymentConfig
    endpointArn string
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    inferenceComponentName string
    The name of the inference component.
    runtimeConfig InferenceComponentRuntimeConfig
    tags Tag[]
    variantName string
    The name of the production variant that hosts the inference component.
    endpoint_name str
    The name of the endpoint that hosts the inference component.
    specification InferenceComponentSpecificationArgs
    deployment_config InferenceComponentDeploymentConfigArgs
    endpoint_arn str
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    inference_component_name str
    The name of the inference component.
    runtime_config InferenceComponentRuntimeConfigArgs
    tags Sequence[TagArgs]
    variant_name str
    The name of the production variant that hosts the inference component.
    endpointName String
    The name of the endpoint that hosts the inference component.
    specification Property Map
    deploymentConfig Property Map
    endpointArn String
    The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
    inferenceComponentName String
    The name of the inference component.
    runtimeConfig Property Map
    tags List<Property Map>
    variantName String
    The name of the production variant that hosts the inference component.

    Outputs

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

    CreationTime string
    The time when the inference component was created.
    FailureReason string
    Id string
    The provider-assigned unique ID for this managed resource.
    InferenceComponentArn string
    The Amazon Resource Name (ARN) of the inference component.
    InferenceComponentStatus Pulumi.AwsNative.SageMaker.InferenceComponentStatus
    The status of the inference component.
    LastModifiedTime string
    The time when the inference component was last updated.
    CreationTime string
    The time when the inference component was created.
    FailureReason string
    Id string
    The provider-assigned unique ID for this managed resource.
    InferenceComponentArn string
    The Amazon Resource Name (ARN) of the inference component.
    InferenceComponentStatus InferenceComponentStatus
    The status of the inference component.
    LastModifiedTime string
    The time when the inference component was last updated.
    creationTime String
    The time when the inference component was created.
    failureReason String
    id String
    The provider-assigned unique ID for this managed resource.
    inferenceComponentArn String
    The Amazon Resource Name (ARN) of the inference component.
    inferenceComponentStatus InferenceComponentStatus
    The status of the inference component.
    lastModifiedTime String
    The time when the inference component was last updated.
    creationTime string
    The time when the inference component was created.
    failureReason string
    id string
    The provider-assigned unique ID for this managed resource.
    inferenceComponentArn string
    The Amazon Resource Name (ARN) of the inference component.
    inferenceComponentStatus InferenceComponentStatus
    The status of the inference component.
    lastModifiedTime string
    The time when the inference component was last updated.
    creation_time str
    The time when the inference component was created.
    failure_reason str
    id str
    The provider-assigned unique ID for this managed resource.
    inference_component_arn str
    The Amazon Resource Name (ARN) of the inference component.
    inference_component_status InferenceComponentStatus
    The status of the inference component.
    last_modified_time str
    The time when the inference component was last updated.
    creationTime String
    The time when the inference component was created.
    failureReason String
    id String
    The provider-assigned unique ID for this managed resource.
    inferenceComponentArn String
    The Amazon Resource Name (ARN) of the inference component.
    inferenceComponentStatus "InService" | "Creating" | "Updating" | "Failed" | "Deleting"
    The status of the inference component.
    lastModifiedTime String
    The time when the inference component was last updated.

    Supporting Types

    InferenceComponentAlarm, InferenceComponentAlarmArgs

    AlarmName string
    AlarmName string
    alarmName String
    alarmName string
    alarmName String

    InferenceComponentAutoRollbackConfiguration, InferenceComponentAutoRollbackConfigurationArgs

    InferenceComponentCapacitySize, InferenceComponentCapacitySizeArgs

    InferenceComponentCapacitySizeType, InferenceComponentCapacitySizeTypeArgs

    CopyCount
    COPY_COUNT
    CapacityPercent
    CAPACITY_PERCENT
    InferenceComponentCapacitySizeTypeCopyCount
    COPY_COUNT
    InferenceComponentCapacitySizeTypeCapacityPercent
    CAPACITY_PERCENT
    CopyCount
    COPY_COUNT
    CapacityPercent
    CAPACITY_PERCENT
    CopyCount
    COPY_COUNT
    CapacityPercent
    CAPACITY_PERCENT
    COPY_COUNT
    COPY_COUNT
    CAPACITY_PERCENT
    CAPACITY_PERCENT
    "COPY_COUNT"
    COPY_COUNT
    "CAPACITY_PERCENT"
    CAPACITY_PERCENT

    InferenceComponentComputeResourceRequirements, InferenceComponentComputeResourceRequirementsArgs

    MaxMemoryRequiredInMb int
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    MinMemoryRequiredInMb int
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    NumberOfAcceleratorDevicesRequired double
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    NumberOfCpuCoresRequired double
    The number of CPU cores to allocate to run a model that you assign to an inference component.
    MaxMemoryRequiredInMb int
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    MinMemoryRequiredInMb int
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    NumberOfAcceleratorDevicesRequired float64
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    NumberOfCpuCoresRequired float64
    The number of CPU cores to allocate to run a model that you assign to an inference component.
    maxMemoryRequiredInMb Integer
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    minMemoryRequiredInMb Integer
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    numberOfAcceleratorDevicesRequired Double
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    numberOfCpuCoresRequired Double
    The number of CPU cores to allocate to run a model that you assign to an inference component.
    maxMemoryRequiredInMb number
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    minMemoryRequiredInMb number
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    numberOfAcceleratorDevicesRequired number
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    numberOfCpuCoresRequired number
    The number of CPU cores to allocate to run a model that you assign to an inference component.
    max_memory_required_in_mb int
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    min_memory_required_in_mb int
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    number_of_accelerator_devices_required float
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    number_of_cpu_cores_required float
    The number of CPU cores to allocate to run a model that you assign to an inference component.
    maxMemoryRequiredInMb Number
    The maximum MB of memory to allocate to run a model that you assign to an inference component.
    minMemoryRequiredInMb Number
    The minimum MB of memory to allocate to run a model that you assign to an inference component.
    numberOfAcceleratorDevicesRequired Number
    The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
    numberOfCpuCoresRequired Number
    The number of CPU cores to allocate to run a model that you assign to an inference component.

    InferenceComponentContainerSpecification, InferenceComponentContainerSpecificationArgs

    ArtifactUrl string
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    DeployedImage Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentDeployedImage
    Environment Dictionary<string, string>
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    Image string
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.
    ArtifactUrl string
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    DeployedImage InferenceComponentDeployedImage
    Environment map[string]string
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    Image string
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.
    artifactUrl String
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    deployedImage InferenceComponentDeployedImage
    environment Map<String,String>
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    image String
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.
    artifactUrl string
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    deployedImage InferenceComponentDeployedImage
    environment {[key: string]: string}
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    image string
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.
    artifact_url str
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    deployed_image InferenceComponentDeployedImage
    environment Mapping[str, str]
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    image str
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.
    artifactUrl String
    The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).
    deployedImage Property Map
    environment Map<String>
    The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.
    image String
    The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.

    InferenceComponentDeployedImage, InferenceComponentDeployedImageArgs

    ResolutionTime string
    The date and time when the image path for the model resolved to the ResolvedImage
    ResolvedImage string
    The specific digest path of the image hosted in this ProductionVariant .
    SpecifiedImage string
    The image path you specified when you created the model.
    ResolutionTime string
    The date and time when the image path for the model resolved to the ResolvedImage
    ResolvedImage string
    The specific digest path of the image hosted in this ProductionVariant .
    SpecifiedImage string
    The image path you specified when you created the model.
    resolutionTime String
    The date and time when the image path for the model resolved to the ResolvedImage
    resolvedImage String
    The specific digest path of the image hosted in this ProductionVariant .
    specifiedImage String
    The image path you specified when you created the model.
    resolutionTime string
    The date and time when the image path for the model resolved to the ResolvedImage
    resolvedImage string
    The specific digest path of the image hosted in this ProductionVariant .
    specifiedImage string
    The image path you specified when you created the model.
    resolution_time str
    The date and time when the image path for the model resolved to the ResolvedImage
    resolved_image str
    The specific digest path of the image hosted in this ProductionVariant .
    specified_image str
    The image path you specified when you created the model.
    resolutionTime String
    The date and time when the image path for the model resolved to the ResolvedImage
    resolvedImage String
    The specific digest path of the image hosted in this ProductionVariant .
    specifiedImage String
    The image path you specified when you created the model.

    InferenceComponentDeploymentConfig, InferenceComponentDeploymentConfigArgs

    InferenceComponentRollingUpdatePolicy, InferenceComponentRollingUpdatePolicyArgs

    InferenceComponentRuntimeConfig, InferenceComponentRuntimeConfigArgs

    CopyCount int
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    CurrentCopyCount int
    DesiredCopyCount int
    CopyCount int
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    CurrentCopyCount int
    DesiredCopyCount int
    copyCount Integer
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    currentCopyCount Integer
    desiredCopyCount Integer
    copyCount number
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    currentCopyCount number
    desiredCopyCount number
    copy_count int
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    current_copy_count int
    desired_copy_count int
    copyCount Number
    The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.
    currentCopyCount Number
    desiredCopyCount Number

    InferenceComponentSpecification, InferenceComponentSpecificationArgs

    BaseInferenceComponentName string

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    ComputeResourceRequirements Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentComputeResourceRequirements

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    Container Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentContainerSpecification
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    ModelName string
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    StartupParameters Pulumi.AwsNative.SageMaker.Inputs.InferenceComponentStartupParameters
    Settings that take effect while the model container starts up.
    BaseInferenceComponentName string

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    ComputeResourceRequirements InferenceComponentComputeResourceRequirements

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    Container InferenceComponentContainerSpecification
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    ModelName string
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    StartupParameters InferenceComponentStartupParameters
    Settings that take effect while the model container starts up.
    baseInferenceComponentName String

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    computeResourceRequirements InferenceComponentComputeResourceRequirements

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    container InferenceComponentContainerSpecification
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    modelName String
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    startupParameters InferenceComponentStartupParameters
    Settings that take effect while the model container starts up.
    baseInferenceComponentName string

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    computeResourceRequirements InferenceComponentComputeResourceRequirements

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    container InferenceComponentContainerSpecification
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    modelName string
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    startupParameters InferenceComponentStartupParameters
    Settings that take effect while the model container starts up.
    base_inference_component_name str

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    compute_resource_requirements InferenceComponentComputeResourceRequirements

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    container InferenceComponentContainerSpecification
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    model_name str
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    startup_parameters InferenceComponentStartupParameters
    Settings that take effect while the model container starts up.
    baseInferenceComponentName String

    The name of an existing inference component that is to contain the inference component that you're creating with your request.

    Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.

    When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type.

    Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.

    computeResourceRequirements Property Map

    The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.

    Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.

    container Property Map
    Defines a container that provides the runtime environment for a model that you deploy with an inference component.
    modelName String
    The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.
    startupParameters Property Map
    Settings that take effect while the model container starts up.

    InferenceComponentStartupParameters, InferenceComponentStartupParametersArgs

    ContainerStartupHealthCheckTimeoutInSeconds int
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    ModelDataDownloadTimeoutInSeconds int
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.
    ContainerStartupHealthCheckTimeoutInSeconds int
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    ModelDataDownloadTimeoutInSeconds int
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.
    containerStartupHealthCheckTimeoutInSeconds Integer
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    modelDataDownloadTimeoutInSeconds Integer
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.
    containerStartupHealthCheckTimeoutInSeconds number
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    modelDataDownloadTimeoutInSeconds number
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.
    container_startup_health_check_timeout_in_seconds int
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    model_data_download_timeout_in_seconds int
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.
    containerStartupHealthCheckTimeoutInSeconds Number
    The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .
    modelDataDownloadTimeoutInSeconds Number
    The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.

    InferenceComponentStatus, InferenceComponentStatusArgs

    InService
    InService
    Creating
    Creating
    Updating
    Updating
    Failed
    Failed
    Deleting
    Deleting
    InferenceComponentStatusInService
    InService
    InferenceComponentStatusCreating
    Creating
    InferenceComponentStatusUpdating
    Updating
    InferenceComponentStatusFailed
    Failed
    InferenceComponentStatusDeleting
    Deleting
    InService
    InService
    Creating
    Creating
    Updating
    Updating
    Failed
    Failed
    Deleting
    Deleting
    InService
    InService
    Creating
    Creating
    Updating
    Updating
    Failed
    Failed
    Deleting
    Deleting
    IN_SERVICE
    InService
    CREATING
    Creating
    UPDATING
    Updating
    FAILED
    Failed
    DELETING
    Deleting
    "InService"
    InService
    "Creating"
    Creating
    "Updating"
    Updating
    "Failed"
    Failed
    "Deleting"
    Deleting

    Tag, TagArgs

    Key string
    The key name of the tag
    Value string
    The value of the tag
    Key string
    The key name of the tag
    Value string
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag
    key string
    The key name of the tag
    value string
    The value of the tag
    key str
    The key name of the tag
    value str
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag

    Package Details

    Repository
    AWS Native pulumi/pulumi-aws-native
    License
    Apache-2.0
    aws-native logo

    We recommend new projects start with resources from the AWS provider.

    AWS Cloud Control v1.26.0 published on Wednesday, Mar 12, 2025 by Pulumi
    pulumi/pulumi-aws-native