aws-sdk-sagemaker 1.275.0 → 1.276.0

data/lib/aws-sdk-sagemaker/client_api.rb

@@ -1535,6 +1535,7 @@ module Aws::SageMaker
     ModelQuantizationConfig = Shapes::StructureShape.new(name: 'ModelQuantizationConfig')
     ModelRegisterSettings = Shapes::StructureShape.new(name: 'ModelRegisterSettings')
     ModelSetupTime = Shapes::IntegerShape.new(name: 'ModelSetupTime')
+    ModelShardingConfig = Shapes::StructureShape.new(name: 'ModelShardingConfig')
     ModelSortKey = Shapes::StringShape.new(name: 'ModelSortKey')
     ModelStepMetadata = Shapes::StructureShape.new(name: 'ModelStepMetadata')
     ModelSummary = Shapes::StructureShape.new(name: 'ModelSummary')
@@ -3002,6 +3003,7 @@ module Aws::SageMaker
     ClusterInstanceGroupDetails.add_member(:threads_per_core, Shapes::ShapeRef.new(shape: ClusterThreadsPerCore, location_name: "ThreadsPerCore"))
     ClusterInstanceGroupDetails.add_member(:instance_storage_configs, Shapes::ShapeRef.new(shape: ClusterInstanceStorageConfigs, location_name: "InstanceStorageConfigs"))
     ClusterInstanceGroupDetails.add_member(:on_start_deep_health_checks, Shapes::ShapeRef.new(shape: OnStartDeepHealthChecks, location_name: "OnStartDeepHealthChecks"))
+    ClusterInstanceGroupDetails.add_member(:override_vpc_config, Shapes::ShapeRef.new(shape: VpcConfig, location_name: "OverrideVpcConfig"))
     ClusterInstanceGroupDetails.struct_class = Types::ClusterInstanceGroupDetails
 
     ClusterInstanceGroupDetailsList.member = Shapes::ShapeRef.new(shape: ClusterInstanceGroupDetails)
@@ -3014,6 +3016,7 @@ module Aws::SageMaker
     ClusterInstanceGroupSpecification.add_member(:threads_per_core, Shapes::ShapeRef.new(shape: ClusterThreadsPerCore, location_name: "ThreadsPerCore"))
     ClusterInstanceGroupSpecification.add_member(:instance_storage_configs, Shapes::ShapeRef.new(shape: ClusterInstanceStorageConfigs, location_name: "InstanceStorageConfigs"))
     ClusterInstanceGroupSpecification.add_member(:on_start_deep_health_checks, Shapes::ShapeRef.new(shape: OnStartDeepHealthChecks, location_name: "OnStartDeepHealthChecks"))
+    ClusterInstanceGroupSpecification.add_member(:override_vpc_config, Shapes::ShapeRef.new(shape: VpcConfig, location_name: "OverrideVpcConfig"))
     ClusterInstanceGroupSpecification.struct_class = Types::ClusterInstanceGroupSpecification
 
     ClusterInstanceGroupSpecifications.member = Shapes::ShapeRef.new(shape: ClusterInstanceGroupSpecification)
@@ -3044,6 +3047,7 @@ module Aws::SageMaker
     ClusterNodeDetails.add_member(:instance_type, Shapes::ShapeRef.new(shape: ClusterInstanceType, location_name: "InstanceType"))
     ClusterNodeDetails.add_member(:launch_time, Shapes::ShapeRef.new(shape: Timestamp, location_name: "LaunchTime"))
     ClusterNodeDetails.add_member(:life_cycle_config, Shapes::ShapeRef.new(shape: ClusterLifeCycleConfig, location_name: "LifeCycleConfig"))
+    ClusterNodeDetails.add_member(:override_vpc_config, Shapes::ShapeRef.new(shape: VpcConfig, location_name: "OverrideVpcConfig"))
     ClusterNodeDetails.add_member(:threads_per_core, Shapes::ShapeRef.new(shape: ClusterThreadsPerCore, location_name: "ThreadsPerCore"))
     ClusterNodeDetails.add_member(:instance_storage_configs, Shapes::ShapeRef.new(shape: ClusterInstanceStorageConfigs, location_name: "InstanceStorageConfigs"))
     ClusterNodeDetails.add_member(:private_primary_ip, Shapes::ShapeRef.new(shape: ClusterPrivatePrimaryIp, location_name: "PrivatePrimaryIp"))
@@ -3535,9 +3539,9 @@ module Aws::SageMaker
 
     CreateInferenceComponentInput.add_member(:inference_component_name, Shapes::ShapeRef.new(shape: InferenceComponentName, required: true, location_name: "InferenceComponentName"))
     CreateInferenceComponentInput.add_member(:endpoint_name, Shapes::ShapeRef.new(shape: EndpointName, required: true, location_name: "EndpointName"))
-    CreateInferenceComponentInput.add_member(:variant_name, Shapes::ShapeRef.new(shape: VariantName, required: true, location_name: "VariantName"))
+    CreateInferenceComponentInput.add_member(:variant_name, Shapes::ShapeRef.new(shape: VariantName, location_name: "VariantName"))
     CreateInferenceComponentInput.add_member(:specification, Shapes::ShapeRef.new(shape: InferenceComponentSpecification, required: true, location_name: "Specification"))
-    CreateInferenceComponentInput.add_member(:runtime_config, Shapes::ShapeRef.new(shape: InferenceComponentRuntimeConfig, required: true, location_name: "RuntimeConfig"))
+    CreateInferenceComponentInput.add_member(:runtime_config, Shapes::ShapeRef.new(shape: InferenceComponentRuntimeConfig, location_name: "RuntimeConfig"))
     CreateInferenceComponentInput.add_member(:tags, Shapes::ShapeRef.new(shape: TagList, location_name: "Tags"))
     CreateInferenceComponentInput.struct_class = Types::CreateInferenceComponentInput
 
@@ -6411,13 +6415,15 @@ module Aws::SageMaker
     InferenceComponentSpecification.add_member(:model_name, Shapes::ShapeRef.new(shape: ModelName, location_name: "ModelName"))
     InferenceComponentSpecification.add_member(:container, Shapes::ShapeRef.new(shape: InferenceComponentContainerSpecification, location_name: "Container"))
     InferenceComponentSpecification.add_member(:startup_parameters, Shapes::ShapeRef.new(shape: InferenceComponentStartupParameters, location_name: "StartupParameters"))
-    InferenceComponentSpecification.add_member(:compute_resource_requirements, Shapes::ShapeRef.new(shape: InferenceComponentComputeResourceRequirements, required: true, location_name: "ComputeResourceRequirements"))
+    InferenceComponentSpecification.add_member(:compute_resource_requirements, Shapes::ShapeRef.new(shape: InferenceComponentComputeResourceRequirements, location_name: "ComputeResourceRequirements"))
+    InferenceComponentSpecification.add_member(:base_inference_component_name, Shapes::ShapeRef.new(shape: InferenceComponentName, location_name: "BaseInferenceComponentName"))
     InferenceComponentSpecification.struct_class = Types::InferenceComponentSpecification
 
     InferenceComponentSpecificationSummary.add_member(:model_name, Shapes::ShapeRef.new(shape: ModelName, location_name: "ModelName"))
     InferenceComponentSpecificationSummary.add_member(:container, Shapes::ShapeRef.new(shape: InferenceComponentContainerSpecificationSummary, location_name: "Container"))
     InferenceComponentSpecificationSummary.add_member(:startup_parameters, Shapes::ShapeRef.new(shape: InferenceComponentStartupParameters, location_name: "StartupParameters"))
     InferenceComponentSpecificationSummary.add_member(:compute_resource_requirements, Shapes::ShapeRef.new(shape: InferenceComponentComputeResourceRequirements, location_name: "ComputeResourceRequirements"))
+    InferenceComponentSpecificationSummary.add_member(:base_inference_component_name, Shapes::ShapeRef.new(shape: InferenceComponentName, location_name: "BaseInferenceComponentName"))
     InferenceComponentSpecificationSummary.struct_class = Types::InferenceComponentSpecificationSummary
 
     InferenceComponentStartupParameters.add_member(:model_data_download_timeout_in_seconds, Shapes::ShapeRef.new(shape: ProductionVariantModelDataDownloadTimeoutInSeconds, location_name: "ModelDataDownloadTimeoutInSeconds"))
@@ -8173,6 +8179,10 @@ module Aws::SageMaker
     ModelRegisterSettings.add_member(:cross_account_model_register_role_arn, Shapes::ShapeRef.new(shape: RoleArn, location_name: "CrossAccountModelRegisterRoleArn"))
     ModelRegisterSettings.struct_class = Types::ModelRegisterSettings
 
+    ModelShardingConfig.add_member(:image, Shapes::ShapeRef.new(shape: OptimizationContainerImage, location_name: "Image"))
+    ModelShardingConfig.add_member(:override_environment, Shapes::ShapeRef.new(shape: OptimizationJobEnvironmentVariables, location_name: "OverrideEnvironment"))
+    ModelShardingConfig.struct_class = Types::ModelShardingConfig
+
     ModelStepMetadata.add_member(:arn, Shapes::ShapeRef.new(shape: String256, location_name: "Arn"))
     ModelStepMetadata.struct_class = Types::ModelStepMetadata
 
@@ -8476,9 +8486,11 @@ module Aws::SageMaker
 
     OptimizationConfig.add_member(:model_quantization_config, Shapes::ShapeRef.new(shape: ModelQuantizationConfig, location_name: "ModelQuantizationConfig"))
     OptimizationConfig.add_member(:model_compilation_config, Shapes::ShapeRef.new(shape: ModelCompilationConfig, location_name: "ModelCompilationConfig"))
+    OptimizationConfig.add_member(:model_sharding_config, Shapes::ShapeRef.new(shape: ModelShardingConfig, location_name: "ModelShardingConfig"))
     OptimizationConfig.add_member(:unknown, Shapes::ShapeRef.new(shape: nil, location_name: 'unknown'))
     OptimizationConfig.add_member_subclass(:model_quantization_config, Types::OptimizationConfig::ModelQuantizationConfig)
     OptimizationConfig.add_member_subclass(:model_compilation_config, Types::OptimizationConfig::ModelCompilationConfig)
+    OptimizationConfig.add_member_subclass(:model_sharding_config, Types::OptimizationConfig::ModelShardingConfig)
     OptimizationConfig.add_member_subclass(:unknown, Types::OptimizationConfig::Unknown)
     OptimizationConfig.struct_class = Types::OptimizationConfig
 

data/lib/aws-sdk-sagemaker/types.rb

@@ -4227,6 +4227,18 @@ module Aws::SageMaker
     #   when the cluster instance group is created or updated.
     #   @return [Array<String>]
     #
+    # @!attribute [rw] override_vpc_config
+    #   Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker
+    #   jobs, hosted models, and compute resources have access to. You can
+    #   control access to and from your resources by configuring a VPC. For
+    #   more information, see [Give SageMaker Access to Resources in your
+    #   Amazon VPC][1].
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html
+    #   @return [Types::VpcConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterInstanceGroupDetails AWS API Documentation
     #
     class ClusterInstanceGroupDetails < Struct.new(
@@ -4238,7 +4250,8 @@ module Aws::SageMaker
       :execution_role,
       :threads_per_core,
       :instance_storage_configs,
-      :on_start_deep_health_checks)
+      :on_start_deep_health_checks,
+      :override_vpc_config)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -4290,6 +4303,18 @@ module Aws::SageMaker
     #   when the cluster instance group is created or updated.
     #   @return [Array<String>]
     #
+    # @!attribute [rw] override_vpc_config
+    #   Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker
+    #   jobs, hosted models, and compute resources have access to. You can
+    #   control access to and from your resources by configuring a VPC. For
+    #   more information, see [Give SageMaker Access to Resources in your
+    #   Amazon VPC][1].
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html
+    #   @return [Types::VpcConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterInstanceGroupSpecification AWS API Documentation
     #
     class ClusterInstanceGroupSpecification < Struct.new(
@@ -4300,7 +4325,8 @@ module Aws::SageMaker
       :execution_role,
       :threads_per_core,
       :instance_storage_configs,
-      :on_start_deep_health_checks)
+      :on_start_deep_health_checks,
+      :override_vpc_config)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -4437,6 +4463,18 @@ module Aws::SageMaker
     #   The LifeCycle configuration applied to the instance.
     #   @return [Types::ClusterLifeCycleConfig]
     #
+    # @!attribute [rw] override_vpc_config
+    #   Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker
+    #   jobs, hosted models, and compute resources have access to. You can
+    #   control access to and from your resources by configuring a VPC. For
+    #   more information, see [Give SageMaker Access to Resources in your
+    #   Amazon VPC][1].
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html
+    #   @return [Types::VpcConfig]
+    #
     # @!attribute [rw] threads_per_core
     #   The number of threads per CPU core you specified under
     #   `CreateCluster`.
@@ -4469,6 +4507,7 @@ module Aws::SageMaker
       :instance_type,
       :launch_time,
       :life_cycle_config,
+      :override_vpc_config,
       :threads_per_core,
       :instance_storage_configs,
       :private_primary_ip,
@@ -24194,9 +24233,9 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
-    # Defines the compute resources to allocate to run a model that you
-    # assign to an inference component. These resources include CPU cores,
-    # accelerators, and memory.
+    # Defines the compute resources to allocate to run a model, plus any
+    # adapter models, that you assign to an inference component. These
+    # resources include CPU cores, accelerators, and memory.
     #
     # @!attribute [rw] number_of_cpu_cores_required
     #   The number of CPU cores to allocate to run a model that you assign
@@ -24355,17 +24394,45 @@ module Aws::SageMaker
     #   @return [Types::InferenceComponentStartupParameters]
     #
     # @!attribute [rw] compute_resource_requirements
-    #   The compute resources allocated to run the model assigned to the
-    #   inference component.
+    #   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.
     #   @return [Types::InferenceComponentComputeResourceRequirements]
     #
+    # @!attribute [rw] base_inference_component_name
+    #   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.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/InferenceComponentSpecification AWS API Documentation
     #
     class InferenceComponentSpecification < Struct.new(
       :model_name,
       :container,
       :startup_parameters,
-      :compute_resource_requirements)
+      :compute_resource_requirements,
+      :base_inference_component_name)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -24388,17 +24455,23 @@ module Aws::SageMaker
     #   @return [Types::InferenceComponentStartupParameters]
     #
     # @!attribute [rw] compute_resource_requirements
-    #   The compute resources allocated to run the model assigned to the
-    #   inference component.
+    #   The compute resources allocated to run the model, plus any adapter
+    #   models, that you assign to the inference component.
     #   @return [Types::InferenceComponentComputeResourceRequirements]
     #
+    # @!attribute [rw] base_inference_component_name
+    #   The name of the base inference component that contains this
+    #   inference component.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/InferenceComponentSpecificationSummary AWS API Documentation
     #
     class InferenceComponentSpecificationSummary < Struct.new(
       :model_name,
       :container,
       :startup_parameters,
-      :compute_resource_requirements)
+      :compute_resource_requirements,
+      :base_inference_component_name)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -33836,6 +33909,28 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
+    # Settings for the model sharding technique that's applied by a model
+    # optimization job.
+    #
+    # @!attribute [rw] image
+    #   The URI of an LMI DLC in Amazon ECR. SageMaker uses this image to
+    #   run the optimization.
+    #   @return [String]
+    #
+    # @!attribute [rw] override_environment
+    #   Environment variables that override the default ones in the model
+    #   container.
+    #   @return [Hash<String,String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ModelShardingConfig AWS API Documentation
+    #
+    class ModelShardingConfig < Struct.new(
+      :image,
+      :override_environment)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Metadata for Model steps.
     #
     # @!attribute [rw] arn
@@ -35415,11 +35510,17 @@ module Aws::SageMaker
     #   model optimization job.
     #   @return [Types::ModelCompilationConfig]
     #
+    # @!attribute [rw] model_sharding_config
+    #   Settings for the model sharding technique that's applied by a model
+    #   optimization job.
+    #   @return [Types::ModelShardingConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/OptimizationConfig AWS API Documentation
     #
     class OptimizationConfig < Struct.new(
       :model_quantization_config,
       :model_compilation_config,
+      :model_sharding_config,
       :unknown)
       SENSITIVE = []
       include Aws::Structure
@@ -35427,6 +35528,7 @@ module Aws::SageMaker
 
       class ModelQuantizationConfig < OptimizationConfig; end
       class ModelCompilationConfig < OptimizationConfig; end
+      class ModelShardingConfig < OptimizationConfig; end
       class Unknown < OptimizationConfig; end
     end
 

data/lib/aws-sdk-sagemaker.rb

@@ -55,7 +55,7 @@ module Aws::SageMaker
   autoload :EndpointProvider, 'aws-sdk-sagemaker/endpoint_provider'
   autoload :Endpoints, 'aws-sdk-sagemaker/endpoints'
 
-  GEM_VERSION = '1.275.0'
+  GEM_VERSION = '1.276.0'
 
 end