@aws-sdk/client-sagemaker 3.916.0 → 3.917.0

package/dist-cjs/index.js

@@ -9759,6 +9759,7 @@ const se_InferenceComponentSpecification = (input, context) => {
         BaseInferenceComponentName: [],
         ComputeResourceRequirements: (_) => se_InferenceComponentComputeResourceRequirements(_),
         Container: smithyClient._json,
+        DataCacheConfig: smithyClient._json,
         ModelName: [],
         StartupParameters: smithyClient._json,
     });
@@ -15941,6 +15942,11 @@ const de_InferenceComponentContainerSpecificationSummary = (output, context) =>
         Environment: (_) => de_EnvironmentMap(_),
     });
 };
+const de_InferenceComponentDataCacheConfigSummary = (output, context) => {
+    return smithyClient.take(output, {
+        EnableCaching: smithyClient.expectBoolean,
+    });
+};
 const de_InferenceComponentDeploymentConfig = (output, context) => {
     return smithyClient.take(output, {
         AutoRollbackConfiguration: (_) => de_AutoRollbackConfig(_),
@@ -15966,6 +15972,7 @@ const de_InferenceComponentSpecificationSummary = (output, context) => {
         BaseInferenceComponentName: smithyClient.expectString,
         ComputeResourceRequirements: (_) => de_InferenceComponentComputeResourceRequirements(_),
         Container: (_) => de_InferenceComponentContainerSpecificationSummary(_),
+        DataCacheConfig: (_) => de_InferenceComponentDataCacheConfigSummary(_),
         ModelName: smithyClient.expectString,
         StartupParameters: (_) => de_InferenceComponentStartupParameters(_),
     });
@@ -24312,26 +24319,6 @@ const SagemakerServicecatalogStatus = {
     DISABLED: "Disabled",
     ENABLED: "Enabled",
 };
-const ResourceType = {
-    ENDPOINT: "Endpoint",
-    EXPERIMENT: "Experiment",
-    EXPERIMENT_TRIAL: "ExperimentTrial",
-    EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent",
-    FEATURE_GROUP: "FeatureGroup",
-    FEATURE_METADATA: "FeatureMetadata",
-    HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob",
-    IMAGE: "Image",
-    IMAGE_VERSION: "ImageVersion",
-    MODEL: "Model",
-    MODEL_CARD: "ModelCard",
-    MODEL_PACKAGE: "ModelPackage",
-    MODEL_PACKAGE_GROUP: "ModelPackageGroup",
-    PIPELINE: "Pipeline",
-    PIPELINE_EXECUTION: "PipelineExecution",
-    PIPELINE_VERSION: "PipelineVersion",
-    PROJECT: "Project",
-    TRAINING_JOB: "TrainingJob",
-};
 const DescribeModelCardResponseFilterSensitiveLog = (obj) => ({
     ...obj,
     ...(obj.Content && { Content: smithyClient.SENSITIVE_STRING }),
@@ -26534,6 +26521,11 @@ class RetryPipelineExecutionCommand extends smithyClient.Command
     .build() {
 }
 
+const UltraServerHealthStatus = {
+    IMPAIRED: "Impaired",
+    INSUFFICIENT_DATA: "Insufficient-Data",
+    OK: "OK",
+};
 const UserProfileSortKey = {
     CreationTime: "CreationTime",
     LastModifiedTime: "LastModifiedTime",
@@ -28883,6 +28875,26 @@ const waitUntilTransformJobCompletedOrStopped = async (params, input) => {
     return utilWaiter.checkExceptions(result);
 };
 
+const ResourceType = {
+    ENDPOINT: "Endpoint",
+    EXPERIMENT: "Experiment",
+    EXPERIMENT_TRIAL: "ExperimentTrial",
+    EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent",
+    FEATURE_GROUP: "FeatureGroup",
+    FEATURE_METADATA: "FeatureMetadata",
+    HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob",
+    IMAGE: "Image",
+    IMAGE_VERSION: "ImageVersion",
+    MODEL: "Model",
+    MODEL_CARD: "ModelCard",
+    MODEL_PACKAGE: "ModelPackage",
+    MODEL_PACKAGE_GROUP: "ModelPackageGroup",
+    PIPELINE: "Pipeline",
+    PIPELINE_EXECUTION: "PipelineExecution",
+    PIPELINE_VERSION: "PipelineVersion",
+    PROJECT: "Project",
+    TRAINING_JOB: "TrainingJob",
+};
 const HubContentSortBy = {
     CREATION_TIME: "CreationTime",
     HUB_CONTENT_NAME: "HubContentName",
@@ -29180,11 +29192,6 @@ const SortTrialsBy = {
     CREATION_TIME: "CreationTime",
     NAME: "Name",
 };
-const UltraServerHealthStatus = {
-    IMPAIRED: "Impaired",
-    INSUFFICIENT_DATA: "Insufficient-Data",
-    OK: "OK",
-};
 
 Object.defineProperty(exports, "$Command", {
     enumerable: true,

package/dist-es/models/models_3.js

@@ -455,26 +455,6 @@ export const SagemakerServicecatalogStatus = {
     DISABLED: "Disabled",
     ENABLED: "Enabled",
 };
-export const ResourceType = {
-    ENDPOINT: "Endpoint",
-    EXPERIMENT: "Experiment",
-    EXPERIMENT_TRIAL: "ExperimentTrial",
-    EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent",
-    FEATURE_GROUP: "FeatureGroup",
-    FEATURE_METADATA: "FeatureMetadata",
-    HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob",
-    IMAGE: "Image",
-    IMAGE_VERSION: "ImageVersion",
-    MODEL: "Model",
-    MODEL_CARD: "ModelCard",
-    MODEL_PACKAGE: "ModelPackage",
-    MODEL_PACKAGE_GROUP: "ModelPackageGroup",
-    PIPELINE: "Pipeline",
-    PIPELINE_EXECUTION: "PipelineExecution",
-    PIPELINE_VERSION: "PipelineVersion",
-    PROJECT: "Project",
-    TRAINING_JOB: "TrainingJob",
-};
 export const DescribeModelCardResponseFilterSensitiveLog = (obj) => ({
     ...obj,
     ...(obj.Content && { Content: SENSITIVE_STRING }),

package/dist-es/models/models_4.js

@@ -1,3 +1,23 @@
+export const ResourceType = {
+    ENDPOINT: "Endpoint",
+    EXPERIMENT: "Experiment",
+    EXPERIMENT_TRIAL: "ExperimentTrial",
+    EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent",
+    FEATURE_GROUP: "FeatureGroup",
+    FEATURE_METADATA: "FeatureMetadata",
+    HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob",
+    IMAGE: "Image",
+    IMAGE_VERSION: "ImageVersion",
+    MODEL: "Model",
+    MODEL_CARD: "ModelCard",
+    MODEL_PACKAGE: "ModelPackage",
+    MODEL_PACKAGE_GROUP: "ModelPackageGroup",
+    PIPELINE: "Pipeline",
+    PIPELINE_EXECUTION: "PipelineExecution",
+    PIPELINE_VERSION: "PipelineVersion",
+    PROJECT: "Project",
+    TRAINING_JOB: "TrainingJob",
+};
 export const HubContentSortBy = {
     CREATION_TIME: "CreationTime",
     HUB_CONTENT_NAME: "HubContentName",
@@ -295,8 +315,3 @@ export const SortTrialsBy = {
     CREATION_TIME: "CreationTime",
     NAME: "Name",
 };
-export const UltraServerHealthStatus = {
-    IMPAIRED: "Impaired",
-    INSUFFICIENT_DATA: "Insufficient-Data",
-    OK: "OK",
-};

package/dist-es/models/models_5.js

@@ -1,5 +1,10 @@
 import { SENSITIVE_STRING } from "@smithy/smithy-client";
 import { ModelPackageModelCardFilterSensitiveLog, OidcConfigFilterSensitiveLog, } from "./models_2";
+export const UltraServerHealthStatus = {
+    IMPAIRED: "Impaired",
+    INSUFFICIENT_DATA: "Insufficient-Data",
+    OK: "OK",
+};
 export const UserProfileSortKey = {
     CreationTime: "CreationTime",
     LastModifiedTime: "LastModifiedTime",

package/dist-es/protocols/Aws_json1_1.js

@@ -7293,6 +7293,7 @@ const se_InferenceComponentSpecification = (input, context) => {
         BaseInferenceComponentName: [],
         ComputeResourceRequirements: (_) => se_InferenceComponentComputeResourceRequirements(_, context),
         Container: _json,
+        DataCacheConfig: _json,
         ModelName: [],
         StartupParameters: _json,
     });
@@ -13480,6 +13481,11 @@ const de_InferenceComponentContainerSpecificationSummary = (output, context) =>
         Environment: (_) => de_EnvironmentMap(_, context),
     });
 };
+const de_InferenceComponentDataCacheConfigSummary = (output, context) => {
+    return take(output, {
+        EnableCaching: __expectBoolean,
+    });
+};
 const de_InferenceComponentDeploymentConfig = (output, context) => {
     return take(output, {
         AutoRollbackConfiguration: (_) => de_AutoRollbackConfig(_, context),
@@ -13505,6 +13511,7 @@ const de_InferenceComponentSpecificationSummary = (output, context) => {
         BaseInferenceComponentName: __expectString,
         ComputeResourceRequirements: (_) => de_InferenceComponentComputeResourceRequirements(_, context),
         Container: (_) => de_InferenceComponentContainerSpecificationSummary(_, context),
+        DataCacheConfig: (_) => de_InferenceComponentDataCacheConfigSummary(_, context),
         ModelName: __expectString,
         StartupParameters: (_) => de_InferenceComponentStartupParameters(_, context),
     });

package/dist-types/commands/CreateInferenceComponentCommand.d.ts

@@ -60,6 +60,9 @@ declare const CreateInferenceComponentCommand_base: {
  *       MaxMemoryRequiredInMb: Number("int"),
  *     },
  *     BaseInferenceComponentName: "STRING_VALUE",
+ *     DataCacheConfig: { // InferenceComponentDataCacheConfig
+ *       EnableCaching: true || false, // required
+ *     },
  *   },
  *   RuntimeConfig: { // InferenceComponentRuntimeConfig
  *     CopyCount: Number("int"), // required

package/dist-types/commands/CreateLabelingJobCommand.d.ts

@@ -1,6 +1,7 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { CreateLabelingJobRequest, CreateLabelingJobResponse } from "../models/models_1";
+import { CreateLabelingJobRequest } from "../models/models_1";
+import { CreateLabelingJobResponse } from "../models/models_2";
 import { SageMakerClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../SageMakerClient";
 /**
  * @public

package/dist-types/commands/DescribeClusterNodeCommand.d.ts

@@ -1,7 +1,6 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { DescribeClusterNodeRequest } from "../models/models_2";
-import { DescribeClusterNodeResponse } from "../models/models_3";
+import { DescribeClusterNodeRequest, DescribeClusterNodeResponse } from "../models/models_3";
 import { SageMakerClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../SageMakerClient";
 /**
  * @public

package/dist-types/commands/DescribeInferenceComponentCommand.d.ts

@@ -72,6 +72,9 @@ declare const DescribeInferenceComponentCommand_base: {
  * //       MaxMemoryRequiredInMb: Number("int"),
  * //     },
  * //     BaseInferenceComponentName: "STRING_VALUE",
+ * //     DataCacheConfig: { // InferenceComponentDataCacheConfigSummary
+ * //       EnableCaching: true || false, // required
+ * //     },
  * //   },
  * //   RuntimeConfig: { // InferenceComponentRuntimeConfigSummary
  * //     DesiredCopyCount: Number("int"),

package/dist-types/commands/GetScalingConfigurationRecommendationCommand.d.ts

@@ -1,6 +1,7 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { GetScalingConfigurationRecommendationRequest, GetScalingConfigurationRecommendationResponse } from "../models/models_3";
+import { GetScalingConfigurationRecommendationRequest } from "../models/models_3";
+import { GetScalingConfigurationRecommendationResponse } from "../models/models_4";
 import { SageMakerClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../SageMakerClient";
 /**
  * @public

package/dist-types/commands/ListUltraServersByReservedCapacityCommand.d.ts

@@ -1,7 +1,6 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { ListUltraServersByReservedCapacityRequest } from "../models/models_4";
-import { ListUltraServersByReservedCapacityResponse } from "../models/models_5";
+import { ListUltraServersByReservedCapacityRequest, ListUltraServersByReservedCapacityResponse } from "../models/models_5";
 import { SageMakerClientResolvedConfig, ServiceInputTypes, ServiceOutputTypes } from "../SageMakerClient";
 /**
  * @public

package/dist-types/commands/UpdateInferenceComponentCommand.d.ts

@@ -58,6 +58,9 @@ declare const UpdateInferenceComponentCommand_base: {
  *       MaxMemoryRequiredInMb: Number("int"),
  *     },
  *     BaseInferenceComponentName: "STRING_VALUE",
+ *     DataCacheConfig: { // InferenceComponentDataCacheConfig
+ *       EnableCaching: true || false, // required
+ *     },
  *   },
  *   RuntimeConfig: { // InferenceComponentRuntimeConfig
  *     CopyCount: Number("int"), // required

package/dist-types/models/models_1.d.ts

@@ -5757,6 +5757,17 @@ export interface InferenceComponentContainerSpecification {
      */
     Environment?: Record<string, string> | undefined;
 }
+/**
+ * <p>Settings that affect how the inference component caches data.</p>
+ * @public
+ */
+export interface InferenceComponentDataCacheConfig {
+    /**
+     * <p>Sets whether the endpoint that hosts the inference component caches the model artifacts and container image.</p> <p>With caching enabled, the endpoint caches this data in each instance that it provisions for the inference component. That way, the inference component deploys faster during the auto scaling process. If caching isn't enabled, the inference component takes longer to deploy because of the time it spends downloading the data.</p>
+     * @public
+     */
+    EnableCaching: boolean | undefined;
+}
 /**
  * <p>Settings that take effect while the model container starts up.</p>
  * @public
@@ -5803,6 +5814,11 @@ export interface InferenceComponentSpecification {
      * @public
      */
     BaseInferenceComponentName?: string | undefined;
+    /**
+     * <p>Settings that affect how the inference component caches data.</p>
+     * @public
+     */
+    DataCacheConfig?: InferenceComponentDataCacheConfig | undefined;
 }
 /**
  * @public
@@ -6960,13 +6976,3 @@ export interface CreateLabelingJobRequest {
      */
     Tags?: Tag[] | undefined;
 }
-/**
- * @public
- */
-export interface CreateLabelingJobResponse {
-    /**
-     * <p>The Amazon Resource Name (ARN) of the labeling job. You use this ARN to identify the labeling job.</p>
-     * @public
-     */
-    LabelingJobArn: string | undefined;
-}

package/dist-types/models/models_2.d.ts

@@ -1,5 +1,15 @@
 import { ActionSource, ActionStatus, AdditionalInferenceSpecificationDefinition, AlgorithmSpecification, AlgorithmStatus, AlgorithmStatusDetails, AlgorithmValidationSpecification, AppSpecification, AppStatus, AppType, ArtifactSource, AthenaDatasetDefinition, AutoMLCandidate, AutoMLChannel, AutoMLComputeConfig, AutoMLDataSplitConfig, AutoMLJobArtifacts, AutoMLJobChannel, AutoMLJobCompletionCriteria, AutoMLJobConfig, AutoMLJobObjective, AutoMLJobSecondaryStatus, AutoMLJobStatus, AutoMLOutputDataConfig, AutoMLPartialFailureReason, AutoMLProblemTypeConfig, AutoMLProblemTypeConfigName, AutoMLResolvedAttributes, AutoMLSecurityConfig, BatchDataCaptureConfig, BatchStrategy, BatchTransformInput, Bias, CaptureStatus, CfnCreateTemplateProvider, Channel, CheckpointConfig, ClusterAutoScalingConfigOutput, ClusterEventDetail, ClusterInstanceGroupDetails, ClusterNodeProvisioningMode, ClusterNodeRecovery, ClusterOrchestrator, CodeEditorAppImageConfig, FeatureStatus, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, MetricsSource, ModelApprovalStatus, ModelDataSource, OutputDataConfig, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TransformInput, TransformJobDefinition, TransformOutput, TransformResources, UserContext, VpcConfig } from "./models_0";
 import { _InstanceType, ClusterRestrictedInstanceGroupDetails, ClusterStatus, ClusterTieredStorageConfig, CodeRepository, CognitoConfig, CognitoMemberDefinition, CollectionConfiguration, ContainerDefinition, DeviceSelectionConfig, EdgeDeploymentConfig, EndpointInput, HubContentType, IPAddressType, JupyterServerAppSettings, KernelGatewayAppSettings, MetadataProperties, ModelDeployConfig, MonitoringConstraintsResource, MonitoringNetworkConfig, MonitoringOutputConfig, MonitoringResources, MonitoringStatisticsResource, MonitoringStoppingCondition, ProcessingInstanceType, ProcessingS3UploadMode, RetryStrategy, TrainingSpecification, UserSettings } from "./models_1";
+/**
+ * @public
+ */
+export interface CreateLabelingJobResponse {
+    /**
+     * <p>The Amazon Resource Name (ARN) of the labeling job. You use this ARN to identify the labeling job.</p>
+     * @public
+     */
+    LabelingJobArn: string | undefined;
+}
 /**
  * @public
  * @enum
@@ -1501,7 +1511,7 @@ export interface CreateNotebookInstanceInput {
      */
     RootAccess?: RootAccess | undefined;
     /**
-     * <p>The platform identifier of the notebook instance runtime environment.</p>
+     * <p>The platform identifier of the notebook instance runtime environment. The default value is <code>notebook-al2-v2</code>.</p>
      * @public
      */
     PlatformIdentifier?: string | undefined;
@@ -2403,7 +2413,7 @@ export interface ProcessingS3Input {
      */
     S3InputMode?: ProcessingS3InputMode | undefined;
     /**
-     * <p>Whether to distribute the data from Amazon S3 to all processing instances with <code>FullyReplicated</code>, or whether the data from Amazon S3 is shared by Amazon S3 key, downloading one shard of data to each processing instance.</p>
+     * <p>Whether to distribute the data from Amazon S3 to all processing instances with <code>FullyReplicated</code>, or whether the data from Amazon S3 is sharded by Amazon S3 key, downloading one shard of data to each processing instance.</p>
      * @public
      */
     S3DataDistributionType?: ProcessingS3DataDistributionType | undefined;
@@ -6016,26 +6026,6 @@ export interface DescribeClusterEventResponse {
      */
     EventDetails?: ClusterEventDetail | undefined;
 }
-/**
- * @public
- */
-export interface DescribeClusterNodeRequest {
-    /**
-     * <p>The string name or the Amazon Resource Name (ARN) of the SageMaker HyperPod cluster in which the node is.</p>
-     * @public
-     */
-    ClusterName: string | undefined;
-    /**
-     * <p>The ID of the SageMaker HyperPod cluster node.</p>
-     * @public
-     */
-    NodeId?: string | undefined;
-    /**
-     * <p>The logical identifier of the node to describe. You can specify either <code>NodeLogicalId</code> or <code>InstanceId</code>, but not both. <code>NodeLogicalId</code> can be used to describe nodes that are still being provisioned and don't yet have an <code>InstanceId</code> assigned.</p>
-     * @public
-     */
-    NodeLogicalId?: string | undefined;
-}
 /**
  * @internal
  */

package/dist-types/models/models_3.d.ts

@@ -1,6 +1,26 @@
 import { ActivationState, AdditionalInferenceSpecificationDefinition, AgentVersion, AlgorithmSpecification, AmazonQSettings, AppNetworkAccessType, AppSecurityGroupManagement, AppSpecification, AssociationEdgeType, AsyncInferenceConfig, AuthMode, AutoRollbackConfig, Autotune, BatchDataCaptureConfig, BatchStrategy, CapacityReservationPreference, CfnTemplateProviderDetail, Channel, CheckpointConfig, ClusterNodeDetails, InferenceSpecification, ModelApprovalStatus, ModelPackageStatus, ObjectiveStatus, OutputDataConfig, ProductionVariantInstanceType, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TransformInput, TransformOutput, TransformResources, UserContext, VolumeAttachmentStatus, VpcConfig } from "./models_0";
 import { _InstanceType, CognitoConfig, CompilationJobStatus, ComputeQuotaConfig, ComputeQuotaTarget, ContainerDefinition, ContextSource, DataCaptureConfig, DataQualityAppSpecification, DataQualityBaselineConfig, DataQualityJobInput, DefaultSpaceSettings, DeploymentConfig, DockerSettings, DomainSettings, EdgeDeploymentModelConfig, EdgeOutputConfig, EdgePresetDeploymentType, EndpointInfo, ExecutionRoleIdentityConfig, ExplainerConfig, FeatureDefinition, FeatureType, FlowDefinitionOutputConfig, GitConfig, HubContentType, HubS3StorageConfig, HumanLoopActivationConfig, HumanLoopConfig, HumanLoopRequestSource, HumanTaskConfig, HyperParameterTrainingJobDefinition, HyperParameterTuningJobConfig, HyperParameterTuningJobObjectiveType, HyperParameterTuningJobWarmStartConfig, InferenceComponentComputeResourceRequirements, InferenceComponentStartupParameters, InferenceExperimentDataStorageConfig, InferenceExperimentSchedule, InferenceExperimentType, InputConfig, IPAddressType, JobType, LabelingJobAlgorithmsConfig, LabelingJobInputConfig, LabelingJobOutputConfig, LabelingJobStoppingConditions, MetadataProperties, ModelInfrastructureConfig, MonitoringNetworkConfig, MonitoringOutputConfig, MonitoringResources, MonitoringStoppingCondition, NeoVpcConfig, OfflineStoreConfig, OnlineStoreConfig, OutputConfig, Processor, ProductionVariant, ProductionVariantAcceleratorType, ProductionVariantManagedInstanceScaling, ProductionVariantRoutingConfig, ProductionVariantServerlessConfig, RecommendationJobInputConfig, RecommendationJobStoppingConditions, RecommendationJobType, RetryStrategy, SchedulerConfig, SchedulerResourceStatus, ShadowModeConfig, TagPropagation, ThroughputMode, TrustedIdentityPropagationSettings, UnifiedStudioSettings, UserSettings, VendorGuidance } from "./models_1";
 import { CustomizedMetricSpecification, DataCaptureConfigSummary, DataProcessing, DebugHookConfig, DebugRuleConfiguration, DebugRuleEvaluationStatus, DeployedImage, DeploymentRecommendation, DeploymentStageStatusSummary, DerivedInformation, DirectInternetAccess, DriftCheckBaselines, ExperimentConfig, InferenceExecutionConfig, InfraCheckConfig, InstanceMetadataServiceConfiguration, MemberDefinition, ModelBiasAppSpecification, ModelBiasBaselineConfig, ModelBiasJobInput, ModelCardExportOutputConfig, ModelCardSecurityConfig, ModelCardStatus, ModelClientConfig, ModelExplainabilityAppSpecification, ModelExplainabilityBaselineConfig, ModelExplainabilityJobInput, ModelLifeCycle, ModelMetrics, ModelPackageModelCard, ModelPackageSecurityConfig, ModelPackageValidationSpecification, ModelQualityAppSpecification, ModelQualityBaselineConfig, ModelQualityJobInput, MonitoringScheduleConfig, MonitoringType, NetworkConfig, NotebookInstanceAcceleratorType, NotebookInstanceLifecycleHook, NotificationConfiguration, OptimizationConfig, OptimizationJobDeploymentInstanceType, OptimizationJobModelSource, OptimizationJobOutputConfig, OptimizationVpcConfig, OwnershipSettings, ParallelismConfiguration, PartnerAppAuthType, PartnerAppConfig, PartnerAppMaintenanceConfig, PartnerAppType, ProcessingInput, ProcessingOutputConfig, ProcessingResources, ProcessingStoppingCondition, ProfilerConfig, ProfilerRuleConfiguration, RemoteDebugConfig, RootAccess, RuleEvaluationStatus, ServiceCatalogProvisioningDetails, SkipModelValidation, SourceAlgorithmSpecification, SourceIpConfig, SpaceSettings, SpaceSharingSettings, StudioLifecycleConfigAppType, TensorBoardOutputConfig, TrackingServerSize, TrialComponentArtifact, TrialComponentParameterValue, TrialComponentStatus, WorkerAccessConfiguration, WorkforceIpAddressType } from "./models_2";
+/**
+ * @public
+ */
+export interface DescribeClusterNodeRequest {
+    /**
+     * <p>The string name or the Amazon Resource Name (ARN) of the SageMaker HyperPod cluster in which the node is.</p>
+     * @public
+     */
+    ClusterName: string | undefined;
+    /**
+     * <p>The ID of the SageMaker HyperPod cluster node.</p>
+     * @public
+     */
+    NodeId?: string | undefined;
+    /**
+     * <p>The logical identifier of the node to describe. You can specify either <code>NodeLogicalId</code> or <code>InstanceId</code>, but not both. <code>NodeLogicalId</code> can be used to describe nodes that are still being provisioned and don't yet have an <code>InstanceId</code> assigned.</p>
+     * @public
+     */
+    NodeLogicalId?: string | undefined;
+}
 /**
  * @public
  */
@@ -2863,6 +2883,17 @@ export interface InferenceComponentContainerSpecificationSummary {
      */
     Environment?: Record<string, string> | undefined;
 }
+/**
+ * <p>Settings that affect how the inference component caches data.</p>
+ * @public
+ */
+export interface InferenceComponentDataCacheConfigSummary {
+    /**
+     * <p>Indicates whether the inference component caches model artifacts as part of the auto scaling process.</p>
+     * @public
+     */
+    EnableCaching: boolean | undefined;
+}
 /**
  * <p>Details about the resources that are deployed with this inference component.</p>
  * @public
@@ -2893,6 +2924,11 @@ export interface InferenceComponentSpecificationSummary {
      * @public
      */
     BaseInferenceComponentName?: string | undefined;
+    /**
+     * <p>Settings that affect how the inference component caches data.</p>
+     * @public
+     */
+    DataCacheConfig?: InferenceComponentDataCacheConfigSummary | undefined;
 }
 /**
  * @public
@@ -8907,74 +8943,6 @@ export interface ScalingPolicyMetric {
      */
     ModelLatency?: number | undefined;
 }
-/**
- * @public
- */
-export interface GetScalingConfigurationRecommendationResponse {
-    /**
-     * <p>The name of a previously completed Inference Recommender job.</p>
-     * @public
-     */
-    InferenceRecommendationsJobName?: string | undefined;
-    /**
-     * <p>The recommendation ID of a previously completed inference recommendation.</p>
-     * @public
-     */
-    RecommendationId?: string | undefined;
-    /**
-     * <p>The name of an endpoint benchmarked during a previously completed Inference Recommender job.</p>
-     * @public
-     */
-    EndpointName?: string | undefined;
-    /**
-     * <p>The percentage of how much utilization you want an instance to use before autoscaling, which you specified in the request. The default value is 50%.</p>
-     * @public
-     */
-    TargetCpuUtilizationPerCore?: number | undefined;
-    /**
-     * <p>An object representing the anticipated traffic pattern for an endpoint that you specified in the request.</p>
-     * @public
-     */
-    ScalingPolicyObjective?: ScalingPolicyObjective | undefined;
-    /**
-     * <p>An object with a list of metrics that were benchmarked during the previously completed Inference Recommender job.</p>
-     * @public
-     */
-    Metric?: ScalingPolicyMetric | undefined;
-    /**
-     * <p>An object with the recommended values for you to specify when creating an autoscaling policy.</p>
-     * @public
-     */
-    DynamicScalingConfiguration?: DynamicScalingConfiguration | undefined;
-}
-/**
- * @public
- * @enum
- */
-export declare const ResourceType: {
-    readonly ENDPOINT: "Endpoint";
-    readonly EXPERIMENT: "Experiment";
-    readonly EXPERIMENT_TRIAL: "ExperimentTrial";
-    readonly EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent";
-    readonly FEATURE_GROUP: "FeatureGroup";
-    readonly FEATURE_METADATA: "FeatureMetadata";
-    readonly HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob";
-    readonly IMAGE: "Image";
-    readonly IMAGE_VERSION: "ImageVersion";
-    readonly MODEL: "Model";
-    readonly MODEL_CARD: "ModelCard";
-    readonly MODEL_PACKAGE: "ModelPackage";
-    readonly MODEL_PACKAGE_GROUP: "ModelPackageGroup";
-    readonly PIPELINE: "Pipeline";
-    readonly PIPELINE_EXECUTION: "PipelineExecution";
-    readonly PIPELINE_VERSION: "PipelineVersion";
-    readonly PROJECT: "Project";
-    readonly TRAINING_JOB: "TrainingJob";
-};
-/**
- * @public
- */
-export type ResourceType = (typeof ResourceType)[keyof typeof ResourceType];
 /**
  * @internal
  */

package/dist-types/models/models_4.d.ts

@@ -1,7 +1,75 @@
 import { ActionSummary, AlgorithmSortBy, AlgorithmSummary, AppDetails, AppImageConfigDetails, AppImageConfigSortKey, AppSortKey, AppType, ArtifactSummary, AssociationEdgeType, AssociationSummary, AutoMLCandidate, AutoMLJobStatus, AutoMLJobStepMetadata, AutoMLJobSummary, AutoMLSortBy, AutoMLSortOrder, CacheHitResult, CallbackStepMetadata, CandidateSortBy, CandidateStatus, ClarifyCheckStepMetadata, ClusterEventResourceType, ClusterEventSummary, ClusterNodeSummary, FeatureStatus, ModelApprovalStatus, ModelPackageStatus, OutputParameter, Tag, UserContext } from "./models_0";
 import { _InstanceType, ClusterSchedulerConfigSummary, ClusterSortBy, ClusterSummary, CodeRepositorySortBy, CodeRepositorySortOrder, CodeRepositorySummary, CompilationJobStatus, CompilationJobSummary, ComputeQuotaSummary, ConditionStepMetadata, ContextSummary, HubContentType, HyperParameterTrainingJobDefinition, HyperParameterTuningJobConfig, HyperParameterTuningJobStrategyType, HyperParameterTuningJobWarmStartConfig, InferenceExperimentSchedule, InferenceExperimentType, LabelingJobInputConfig, RecommendationJobType, ResourceLimits, SchedulerResourceStatus } from "./models_1";
 import { CrossAccountFilterOption, ModelCardStatus, ModelLifeCycle, MonitoringType, OptimizationJobDeploymentInstanceType, PartnerAppType, SharingType, SpaceStorageSettings, StudioLifecycleConfigAppType, TrialComponentStatus } from "./models_2";
-import { DeviceDeploymentSummary, DeviceFleetSummary, DeviceSummary, DomainDetails, EdgeDeploymentPlanSummary, EdgePackagingJobStatus, EdgePackagingJobSummary, EMRStepMetadata, EndpointConfigSortKey, EndpointConfigStepMetadata, EndpointConfigSummary, EndpointOutputConfiguration, EndpointSortKey, EndpointStatus, EndpointStepMetadata, EndpointSummary, EventSortBy, ExecutionStatus, ExperimentSummary, FailStepMetadata, FeatureGroupSortBy, FeatureGroupSortOrder, FeatureGroupStatus, FeatureGroupSummary, FlowDefinitionSummary, HubContentStatus, HubContentSupportStatus, HubStatus, HyperParameterTrainingJobSummary, HyperParameterTuningJobCompletionDetails, HyperParameterTuningJobConsumedResources, HyperParameterTuningJobStatus, ImageStatus, ImageVersionStatus, InferenceComponentStatus, InferenceExperimentStatus, InferenceMetrics, IsTrackingServerActive, LabelCounters, LabelingJobOutput, LabelingJobStatus, ModelCardExportJobStatus, ModelConfiguration, ModelPackageGroupStatus, MonitoringExecutionSummary, NotebookInstanceStatus, ObjectiveStatusCounters, OfflineStoreStatusValue, OptimizationJobStatus, PartnerAppStatus, PipelineExecutionStatus, ProcessingJobStatus, ProjectStatus, RecommendationJobStatus, RecommendationMetrics, ReservedCapacitySummary, ResourceType, SageMakerResourceName, ScheduleStatus, SecondaryStatus, SpaceStatus, SubscribedWorkteam, TrackingServerStatus, TrainingJobStatus, TrainingJobStatusCounters, TrainingPlanStatus, TransformJobStatus, TrialComponentSource, TrialSource, WarmPoolResourceStatus, WarmPoolStatus } from "./models_3";
+import { DeviceDeploymentSummary, DeviceFleetSummary, DeviceSummary, DomainDetails, DynamicScalingConfiguration, EdgeDeploymentPlanSummary, EdgePackagingJobStatus, EdgePackagingJobSummary, EMRStepMetadata, EndpointConfigSortKey, EndpointConfigStepMetadata, EndpointConfigSummary, EndpointOutputConfiguration, EndpointSortKey, EndpointStatus, EndpointStepMetadata, EndpointSummary, EventSortBy, ExecutionStatus, ExperimentSummary, FailStepMetadata, FeatureGroupSortBy, FeatureGroupSortOrder, FeatureGroupStatus, FeatureGroupSummary, FlowDefinitionSummary, HubContentStatus, HubContentSupportStatus, HubStatus, HyperParameterTrainingJobSummary, HyperParameterTuningJobCompletionDetails, HyperParameterTuningJobConsumedResources, HyperParameterTuningJobStatus, ImageStatus, ImageVersionStatus, InferenceComponentStatus, InferenceExperimentStatus, InferenceMetrics, IsTrackingServerActive, LabelCounters, LabelingJobOutput, LabelingJobStatus, ModelCardExportJobStatus, ModelConfiguration, ModelPackageGroupStatus, MonitoringExecutionSummary, NotebookInstanceStatus, ObjectiveStatusCounters, OfflineStoreStatusValue, OptimizationJobStatus, PartnerAppStatus, PipelineExecutionStatus, ProcessingJobStatus, ProjectStatus, RecommendationJobStatus, RecommendationMetrics, ReservedCapacitySummary, SageMakerResourceName, ScalingPolicyMetric, ScalingPolicyObjective, ScheduleStatus, SecondaryStatus, SpaceStatus, SubscribedWorkteam, TrackingServerStatus, TrainingJobStatus, TrainingJobStatusCounters, TrainingPlanStatus, TransformJobStatus, TrialComponentSource, TrialSource, WarmPoolResourceStatus, WarmPoolStatus } from "./models_3";
+/**
+ * @public
+ */
+export interface GetScalingConfigurationRecommendationResponse {
+    /**
+     * <p>The name of a previously completed Inference Recommender job.</p>
+     * @public
+     */
+    InferenceRecommendationsJobName?: string | undefined;
+    /**
+     * <p>The recommendation ID of a previously completed inference recommendation.</p>
+     * @public
+     */
+    RecommendationId?: string | undefined;
+    /**
+     * <p>The name of an endpoint benchmarked during a previously completed Inference Recommender job.</p>
+     * @public
+     */
+    EndpointName?: string | undefined;
+    /**
+     * <p>The percentage of how much utilization you want an instance to use before autoscaling, which you specified in the request. The default value is 50%.</p>
+     * @public
+     */
+    TargetCpuUtilizationPerCore?: number | undefined;
+    /**
+     * <p>An object representing the anticipated traffic pattern for an endpoint that you specified in the request.</p>
+     * @public
+     */
+    ScalingPolicyObjective?: ScalingPolicyObjective | undefined;
+    /**
+     * <p>An object with a list of metrics that were benchmarked during the previously completed Inference Recommender job.</p>
+     * @public
+     */
+    Metric?: ScalingPolicyMetric | undefined;
+    /**
+     * <p>An object with the recommended values for you to specify when creating an autoscaling policy.</p>
+     * @public
+     */
+    DynamicScalingConfiguration?: DynamicScalingConfiguration | undefined;
+}
+/**
+ * @public
+ * @enum
+ */
+export declare const ResourceType: {
+    readonly ENDPOINT: "Endpoint";
+    readonly EXPERIMENT: "Experiment";
+    readonly EXPERIMENT_TRIAL: "ExperimentTrial";
+    readonly EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent";
+    readonly FEATURE_GROUP: "FeatureGroup";
+    readonly FEATURE_METADATA: "FeatureMetadata";
+    readonly HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob";
+    readonly IMAGE: "Image";
+    readonly IMAGE_VERSION: "ImageVersion";
+    readonly MODEL: "Model";
+    readonly MODEL_CARD: "ModelCard";
+    readonly MODEL_PACKAGE: "ModelPackage";
+    readonly MODEL_PACKAGE_GROUP: "ModelPackageGroup";
+    readonly PIPELINE: "Pipeline";
+    readonly PIPELINE_EXECUTION: "PipelineExecution";
+    readonly PIPELINE_VERSION: "PipelineVersion";
+    readonly PROJECT: "Project";
+    readonly TRAINING_JOB: "TrainingJob";
+};
+/**
+ * @public
+ */
+export type ResourceType = (typeof ResourceType)[keyof typeof ResourceType];
 /**
  * <p>Part of the <code>SuggestionQuery</code> type. Specifies a hint for retrieving property names that begin with the specified text.</p>
  * @public
@@ -8148,36 +8216,3 @@ export interface ListTrialsResponse {
      */
     NextToken?: string | undefined;
 }
-/**
- * @public
- */
-export interface ListUltraServersByReservedCapacityRequest {
-    /**
-     * <p>The ARN of the reserved capacity to list UltraServers for.</p>
-     * @public
-     */
-    ReservedCapacityArn: string | undefined;
-    /**
-     * <p>The maximum number of UltraServers to return in the response. The default value is 10.</p>
-     * @public
-     */
-    MaxResults?: number | undefined;
-    /**
-     * <p>If the previous response was truncated, you receive this token. Use it in your next request to receive the next set of results.</p>
-     * @public
-     */
-    NextToken?: string | undefined;
-}
-/**
- * @public
- * @enum
- */
-export declare const UltraServerHealthStatus: {
-    readonly IMPAIRED: "Impaired";
-    readonly INSUFFICIENT_DATA: "Insufficient-Data";
-    readonly OK: "OK";
-};
-/**
- * @public
- */
-export type UltraServerHealthStatus = (typeof UltraServerHealthStatus)[keyof typeof UltraServerHealthStatus];

package/dist-types/models/models_5.d.ts

@@ -1,8 +1,41 @@
 import { ActionStatus, ActivationState, AdditionalInferenceSpecificationDefinition, AlgorithmSpecification, AppNetworkAccessType, AppSecurityGroupManagement, AppSpecification, BatchDataCaptureConfig, BatchStrategy, BatchTransformInput, BooleanOperator, CfnUpdateTemplateProvider, Channel, CheckpointConfig, ClusterAutoScalingConfig, ClusterInstanceGroupSpecification, ClusterNodeRecovery, CodeEditorAppImageConfig, DeploymentConfiguration, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, ModelApprovalStatus, ModelPackageStatus, OutputDataConfig, OutputParameter, ResourceConfig, StoppingCondition, Tag, TransformInput, TransformOutput, TransformResources, UserContext, VpcConfig } from "./models_0";
 import { _InstanceType, ClusterRestrictedInstanceGroupSpecification, ClusterTieredStorageConfig, ComputeQuotaConfig, ComputeQuotaTarget, ContainerDefinition, DefaultSpaceSettings, DeploymentConfig, EdgeOutputConfig, FeatureDefinition, HubContentType, InferenceComponentRuntimeConfig, InferenceComponentSpecification, InferenceExperimentDataStorageConfig, InferenceExperimentSchedule, IPAddressType, JobType, MetadataProperties, ModelVariantConfig, Processor, RetryStrategy, SchedulerConfig, ShadowModeConfig, TagPropagation, ThroughputMode, TtlDuration, UiTemplate, UserSettings, VendorGuidance } from "./models_1";
 import { CrossAccountFilterOption, DataProcessing, DebugHookConfig, DebugRuleConfiguration, DebugRuleEvaluationStatus, DeploymentRecommendation, DriftCheckBaselines, ExperimentConfig, InferenceExecutionConfig, InstanceMetadataServiceConfiguration, MemberDefinition, ModelCardSecurityConfig, ModelCardStatus, ModelClientConfig, ModelLifeCycle, ModelMetrics, ModelPackageModelCard, ModelPackageSecurityConfig, ModelPackageValidationSpecification, MonitoringScheduleConfig, MonitoringType, NetworkConfig, NotebookInstanceAcceleratorType, NotebookInstanceLifecycleHook, NotificationConfiguration, OidcConfig, ParallelismConfiguration, PartnerAppConfig, PartnerAppMaintenanceConfig, PipelineDefinitionS3Location, ProcessingInput, ProcessingOutputConfig, ProcessingResources, ProcessingStoppingCondition, ProfilerConfig, ProfilerRuleConfiguration, ProvisioningParameter, RootAccess, ServiceCatalogProvisioningDetails, SkipModelValidation, SourceAlgorithmSpecification, SourceIpConfig, SpaceSettings, TensorBoardOutputConfig, TrackingServerSize, TrialComponentArtifact, TrialComponentParameterValue, TrialComponentStatus, WorkerAccessConfiguration, WorkforceIpAddressType, WorkforceVpcConfigRequest } from "./models_2";
-import { DesiredWeightAndCapacity, Device, Direction, DomainSettingsForUpdate, Edge, Endpoint, EndpointStatus, Experiment, FeatureGroup, FeatureMetadata, FeatureParameter, Filter, HubContentSupportStatus, InferenceComponentDeploymentConfig, MetricData, ModelArtifacts, ModelPackageGroupStatus, ModelPackageStatusDetails, MonitoringExecutionSummary, PipelineExecutionStatus, PipelineExperimentConfig, PipelineStatus, ProcessingJobStatus, ProjectStatus, ReservedCapacityInstanceType, ReservedCapacityType, ResourceType, SageMakerResourceName, ScheduleStatus, SecondaryStatus, SecondaryStatusTransition, SelectiveExecutionConfig, ServiceCatalogProvisionedProductDetails, TemplateProviderDetail, TrainingJobStatus, TransformJobStatus, TrialComponentMetricSummary, TrialComponentSource, TrialSource, UserProfileStatus, Workforce, Workteam } from "./models_3";
-import { GitConfigForUpdate, HyperParameterTuningJobSearchEntity, InferenceExperimentStopDesiredState, LineageType, MonitoringAlertSummary, Parameter, SortOrder, UltraServerHealthStatus } from "./models_4";
+import { DesiredWeightAndCapacity, Device, Direction, DomainSettingsForUpdate, Edge, Endpoint, EndpointStatus, Experiment, FeatureGroup, FeatureMetadata, FeatureParameter, Filter, HubContentSupportStatus, InferenceComponentDeploymentConfig, MetricData, ModelArtifacts, ModelPackageGroupStatus, ModelPackageStatusDetails, MonitoringExecutionSummary, PipelineExecutionStatus, PipelineExperimentConfig, PipelineStatus, ProcessingJobStatus, ProjectStatus, ReservedCapacityInstanceType, ReservedCapacityType, SageMakerResourceName, ScheduleStatus, SecondaryStatus, SecondaryStatusTransition, SelectiveExecutionConfig, ServiceCatalogProvisionedProductDetails, TemplateProviderDetail, TrainingJobStatus, TransformJobStatus, TrialComponentMetricSummary, TrialComponentSource, TrialSource, UserProfileStatus, Workforce, Workteam } from "./models_3";
+import { GitConfigForUpdate, HyperParameterTuningJobSearchEntity, InferenceExperimentStopDesiredState, LineageType, MonitoringAlertSummary, Parameter, ResourceType, SortOrder } from "./models_4";
+/**
+ * @public
+ */
+export interface ListUltraServersByReservedCapacityRequest {
+    /**
+     * <p>The ARN of the reserved capacity to list UltraServers for.</p>
+     * @public
+     */
+    ReservedCapacityArn: string | undefined;
+    /**
+     * <p>The maximum number of UltraServers to return in the response. The default value is 10.</p>
+     * @public
+     */
+    MaxResults?: number | undefined;
+    /**
+     * <p>If the previous response was truncated, you receive this token. Use it in your next request to receive the next set of results.</p>
+     * @public
+     */
+    NextToken?: string | undefined;
+}
+/**
+ * @public
+ * @enum
+ */
+export declare const UltraServerHealthStatus: {
+    readonly IMPAIRED: "Impaired";
+    readonly INSUFFICIENT_DATA: "Insufficient-Data";
+    readonly OK: "OK";
+};
+/**
+ * @public
+ */
+export type UltraServerHealthStatus = (typeof UltraServerHealthStatus)[keyof typeof UltraServerHealthStatus];
 /**
  * <p>Represents a high-performance compute server used for distributed training in SageMaker AI. An UltraServer consists of multiple instances within a shared NVLink interconnect domain.</p>
  * @public

package/dist-types/ts3.4/commands/CreateLabelingJobCommand.d.ts

@@ -1,9 +1,7 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import {
-  CreateLabelingJobRequest,
-  CreateLabelingJobResponse,
-} from "../models/models_1";
+import { CreateLabelingJobRequest } from "../models/models_1";
+import { CreateLabelingJobResponse } from "../models/models_2";
 import {
   SageMakerClientResolvedConfig,
   ServiceInputTypes,

package/dist-types/ts3.4/commands/DescribeClusterNodeCommand.d.ts

@@ -1,7 +1,9 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { DescribeClusterNodeRequest } from "../models/models_2";
-import { DescribeClusterNodeResponse } from "../models/models_3";
+import {
+  DescribeClusterNodeRequest,
+  DescribeClusterNodeResponse,
+} from "../models/models_3";
 import {
   SageMakerClientResolvedConfig,
   ServiceInputTypes,

package/dist-types/ts3.4/commands/GetScalingConfigurationRecommendationCommand.d.ts

@@ -1,9 +1,7 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import {
-  GetScalingConfigurationRecommendationRequest,
-  GetScalingConfigurationRecommendationResponse,
-} from "../models/models_3";
+import { GetScalingConfigurationRecommendationRequest } from "../models/models_3";
+import { GetScalingConfigurationRecommendationResponse } from "../models/models_4";
 import {
   SageMakerClientResolvedConfig,
   ServiceInputTypes,

package/dist-types/ts3.4/commands/ListUltraServersByReservedCapacityCommand.d.ts

@@ -1,7 +1,9 @@
 import { Command as $Command } from "@smithy/smithy-client";
 import { MetadataBearer as __MetadataBearer } from "@smithy/types";
-import { ListUltraServersByReservedCapacityRequest } from "../models/models_4";
-import { ListUltraServersByReservedCapacityResponse } from "../models/models_5";
+import {
+  ListUltraServersByReservedCapacityRequest,
+  ListUltraServersByReservedCapacityResponse,
+} from "../models/models_5";
 import {
   SageMakerClientResolvedConfig,
   ServiceInputTypes,

package/dist-types/ts3.4/models/models_1.d.ts

@@ -1831,6 +1831,9 @@ export interface InferenceComponentContainerSpecification {
   ArtifactUrl?: string | undefined;
   Environment?: Record<string, string> | undefined;
 }
+export interface InferenceComponentDataCacheConfig {
+  EnableCaching: boolean | undefined;
+}
 export interface InferenceComponentStartupParameters {
   ModelDataDownloadTimeoutInSeconds?: number | undefined;
   ContainerStartupHealthCheckTimeoutInSeconds?: number | undefined;
@@ -1843,6 +1846,7 @@ export interface InferenceComponentSpecification {
     | InferenceComponentComputeResourceRequirements
     | undefined;
   BaseInferenceComponentName?: string | undefined;
+  DataCacheConfig?: InferenceComponentDataCacheConfig | undefined;
 }
 export interface CreateInferenceComponentInput {
   InferenceComponentName: string | undefined;
@@ -2267,6 +2271,3 @@ export interface CreateLabelingJobRequest {
   HumanTaskConfig: HumanTaskConfig | undefined;
   Tags?: Tag[] | undefined;
 }
-export interface CreateLabelingJobResponse {
-  LabelingJobArn: string | undefined;
-}

package/dist-types/ts3.4/models/models_2.d.ts

@@ -97,6 +97,9 @@ import {
   TrainingSpecification,
   UserSettings,
 } from "./models_1";
+export interface CreateLabelingJobResponse {
+  LabelingJobArn: string | undefined;
+}
 export declare const TrackingServerSize: {
   readonly L: "Large";
   readonly M: "Medium";
@@ -1781,11 +1784,6 @@ export interface DescribeClusterEventRequest {
 export interface DescribeClusterEventResponse {
   EventDetails?: ClusterEventDetail | undefined;
 }
-export interface DescribeClusterNodeRequest {
-  ClusterName: string | undefined;
-  NodeId?: string | undefined;
-  NodeLogicalId?: string | undefined;
-}
 export declare const CreateModelCardRequestFilterSensitiveLog: (
   obj: CreateModelCardRequest
 ) => any;

package/dist-types/ts3.4/models/models_3.d.ts

@@ -191,6 +191,11 @@ import {
   WorkerAccessConfiguration,
   WorkforceIpAddressType,
 } from "./models_2";
+export interface DescribeClusterNodeRequest {
+  ClusterName: string | undefined;
+  NodeId?: string | undefined;
+  NodeLogicalId?: string | undefined;
+}
 export interface DescribeClusterNodeResponse {
   NodeDetails: ClusterNodeDetails | undefined;
 }
@@ -947,6 +952,9 @@ export interface InferenceComponentContainerSpecificationSummary {
   ArtifactUrl?: string | undefined;
   Environment?: Record<string, string> | undefined;
 }
+export interface InferenceComponentDataCacheConfigSummary {
+  EnableCaching: boolean | undefined;
+}
 export interface InferenceComponentSpecificationSummary {
   ModelName?: string | undefined;
   Container?: InferenceComponentContainerSpecificationSummary | undefined;
@@ -955,6 +963,7 @@ export interface InferenceComponentSpecificationSummary {
     | InferenceComponentComputeResourceRequirements
     | undefined;
   BaseInferenceComponentName?: string | undefined;
+  DataCacheConfig?: InferenceComponentDataCacheConfigSummary | undefined;
 }
 export interface DescribeInferenceComponentOutput {
   InferenceComponentName: string | undefined;
@@ -2602,36 +2611,6 @@ export interface ScalingPolicyMetric {
   InvocationsPerInstance?: number | undefined;
   ModelLatency?: number | undefined;
 }
-export interface GetScalingConfigurationRecommendationResponse {
-  InferenceRecommendationsJobName?: string | undefined;
-  RecommendationId?: string | undefined;
-  EndpointName?: string | undefined;
-  TargetCpuUtilizationPerCore?: number | undefined;
-  ScalingPolicyObjective?: ScalingPolicyObjective | undefined;
-  Metric?: ScalingPolicyMetric | undefined;
-  DynamicScalingConfiguration?: DynamicScalingConfiguration | undefined;
-}
-export declare const ResourceType: {
-  readonly ENDPOINT: "Endpoint";
-  readonly EXPERIMENT: "Experiment";
-  readonly EXPERIMENT_TRIAL: "ExperimentTrial";
-  readonly EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent";
-  readonly FEATURE_GROUP: "FeatureGroup";
-  readonly FEATURE_METADATA: "FeatureMetadata";
-  readonly HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob";
-  readonly IMAGE: "Image";
-  readonly IMAGE_VERSION: "ImageVersion";
-  readonly MODEL: "Model";
-  readonly MODEL_CARD: "ModelCard";
-  readonly MODEL_PACKAGE: "ModelPackage";
-  readonly MODEL_PACKAGE_GROUP: "ModelPackageGroup";
-  readonly PIPELINE: "Pipeline";
-  readonly PIPELINE_EXECUTION: "PipelineExecution";
-  readonly PIPELINE_VERSION: "PipelineVersion";
-  readonly PROJECT: "Project";
-  readonly TRAINING_JOB: "TrainingJob";
-};
-export type ResourceType = (typeof ResourceType)[keyof typeof ResourceType];
 export declare const DescribeModelCardResponseFilterSensitiveLog: (
   obj: DescribeModelCardResponse
 ) => any;

package/dist-types/ts3.4/models/models_4.d.ts

@@ -73,6 +73,7 @@ import {
   DeviceFleetSummary,
   DeviceSummary,
   DomainDetails,
+  DynamicScalingConfiguration,
   EdgeDeploymentPlanSummary,
   EdgePackagingJobStatus,
   EdgePackagingJobSummary,
@@ -125,8 +126,9 @@ import {
   RecommendationJobStatus,
   RecommendationMetrics,
   ReservedCapacitySummary,
-  ResourceType,
   SageMakerResourceName,
+  ScalingPolicyMetric,
+  ScalingPolicyObjective,
   ScheduleStatus,
   SecondaryStatus,
   SpaceStatus,
@@ -141,6 +143,36 @@ import {
   WarmPoolResourceStatus,
   WarmPoolStatus,
 } from "./models_3";
+export interface GetScalingConfigurationRecommendationResponse {
+  InferenceRecommendationsJobName?: string | undefined;
+  RecommendationId?: string | undefined;
+  EndpointName?: string | undefined;
+  TargetCpuUtilizationPerCore?: number | undefined;
+  ScalingPolicyObjective?: ScalingPolicyObjective | undefined;
+  Metric?: ScalingPolicyMetric | undefined;
+  DynamicScalingConfiguration?: DynamicScalingConfiguration | undefined;
+}
+export declare const ResourceType: {
+  readonly ENDPOINT: "Endpoint";
+  readonly EXPERIMENT: "Experiment";
+  readonly EXPERIMENT_TRIAL: "ExperimentTrial";
+  readonly EXPERIMENT_TRIAL_COMPONENT: "ExperimentTrialComponent";
+  readonly FEATURE_GROUP: "FeatureGroup";
+  readonly FEATURE_METADATA: "FeatureMetadata";
+  readonly HYPER_PARAMETER_TUNING_JOB: "HyperParameterTuningJob";
+  readonly IMAGE: "Image";
+  readonly IMAGE_VERSION: "ImageVersion";
+  readonly MODEL: "Model";
+  readonly MODEL_CARD: "ModelCard";
+  readonly MODEL_PACKAGE: "ModelPackage";
+  readonly MODEL_PACKAGE_GROUP: "ModelPackageGroup";
+  readonly PIPELINE: "Pipeline";
+  readonly PIPELINE_EXECUTION: "PipelineExecution";
+  readonly PIPELINE_VERSION: "PipelineVersion";
+  readonly PROJECT: "Project";
+  readonly TRAINING_JOB: "TrainingJob";
+};
+export type ResourceType = (typeof ResourceType)[keyof typeof ResourceType];
 export interface PropertyNameQuery {
   PropertyNameHint: string | undefined;
 }
@@ -2246,15 +2278,3 @@ export interface ListTrialsResponse {
   TrialSummaries?: TrialSummary[] | undefined;
   NextToken?: string | undefined;
 }
-export interface ListUltraServersByReservedCapacityRequest {
-  ReservedCapacityArn: string | undefined;
-  MaxResults?: number | undefined;
-  NextToken?: string | undefined;
-}
-export declare const UltraServerHealthStatus: {
-  readonly IMPAIRED: "Impaired";
-  readonly INSUFFICIENT_DATA: "Insufficient-Data";
-  readonly OK: "OK";
-};
-export type UltraServerHealthStatus =
-  (typeof UltraServerHealthStatus)[keyof typeof UltraServerHealthStatus];

package/dist-types/ts3.4/models/models_5.d.ts

@@ -145,7 +145,6 @@ import {
   ProjectStatus,
   ReservedCapacityInstanceType,
   ReservedCapacityType,
-  ResourceType,
   SageMakerResourceName,
   ScheduleStatus,
   SecondaryStatus,
@@ -169,9 +168,21 @@ import {
   LineageType,
   MonitoringAlertSummary,
   Parameter,
+  ResourceType,
   SortOrder,
-  UltraServerHealthStatus,
 } from "./models_4";
+export interface ListUltraServersByReservedCapacityRequest {
+  ReservedCapacityArn: string | undefined;
+  MaxResults?: number | undefined;
+  NextToken?: string | undefined;
+}
+export declare const UltraServerHealthStatus: {
+  readonly IMPAIRED: "Impaired";
+  readonly INSUFFICIENT_DATA: "Insufficient-Data";
+  readonly OK: "OK";
+};
+export type UltraServerHealthStatus =
+  (typeof UltraServerHealthStatus)[keyof typeof UltraServerHealthStatus];
 export interface UltraServer {
   UltraServerId: string | undefined;
   UltraServerType: string | undefined;

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@aws-sdk/client-sagemaker",
   "description": "AWS SDK for JavaScript Sagemaker Client for Node.js, Browser and React Native",
-  "version": "3.916.0",
+  "version": "3.917.0",
   "scripts": {
     "build": "concurrently 'yarn:build:cjs' 'yarn:build:es' 'yarn:build:types'",
     "build:cjs": "node ../../scripts/compilation/inline client-sagemaker",
@@ -21,7 +21,7 @@
     "@aws-crypto/sha256-browser": "5.2.0",
     "@aws-crypto/sha256-js": "5.2.0",
     "@aws-sdk/core": "3.916.0",
-    "@aws-sdk/credential-provider-node": "3.916.0",
+    "@aws-sdk/credential-provider-node": "3.917.0",
     "@aws-sdk/middleware-host-header": "3.914.0",
     "@aws-sdk/middleware-logger": "3.914.0",
     "@aws-sdk/middleware-recursion-detection": "3.914.0",