@aws-sdk/client-sagemaker 3.693.0 → 3.699.0

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

@@ -1,5 +1,96 @@
 import { ActionSource, ActionStatus, AlgorithmSpecification, AlgorithmStatus, AlgorithmStatusDetails, AlgorithmValidationSpecification, AppNetworkAccessType, AppSecurityGroupManagement, AppSpecification, AppStatus, AppType, ArtifactSource, AsyncInferenceConfig, AthenaDatasetDefinition, AuthMode, AutoMLCandidate, AutoMLChannel, AutoMLComputeConfig, AutoMLDataSplitConfig, AutoMLJobArtifacts, AutoMLJobChannel, AutoMLJobCompletionCriteria, AutoMLJobConfig, AutoMLJobObjective, AutoMLJobSecondaryStatus, AutoMLJobStatus, AutoMLOutputDataConfig, AutoMLPartialFailureReason, AutoMLProblemTypeConfig, AutoMLProblemTypeConfigName, AutoMLResolvedAttributes, AutoMLSecurityConfig, Autotune, BatchDataCaptureConfig, BatchStrategy, CaptureStatus, Channel, CheckpointConfig, ClusterInstanceGroupDetails, ClusterNodeDetails, ClusterNodeRecovery, ClusterOrchestrator, ClusterStatus, CodeEditorAppImageConfig, CodeRepository, CognitoConfig, CognitoMemberDefinition, CollectionConfiguration, CompilationJobStatus, ContextSource, GitConfig, HyperParameterTuningJobObjectiveType, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, MetadataProperties, ObjectiveStatus, OutputDataConfig, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TrainingSpecification, TransformInput, TransformOutput, TransformResources, UserContext, VpcConfig } from "./models_0";
-import { DataCaptureConfig, DataQualityAppSpecification, DataQualityBaselineConfig, DataQualityJobInput, DefaultSpaceSettings, DeploymentConfig, DeviceSelectionConfig, DomainSettings, EdgeDeploymentConfig, EdgeDeploymentModelConfig, EdgeOutputConfig, EdgePresetDeploymentType, EndpointInfo, ExplainerConfig, FeatureDefinition, FeatureType, FlowDefinitionOutputConfig, HubS3StorageConfig, HumanLoopActivationConfig, HumanLoopConfig, HumanLoopRequestSource, HyperParameterTrainingJobDefinition, HyperParameterTuningJobConfig, HyperParameterTuningJobWarmStartConfig, InferenceComponentComputeResourceRequirements, InferenceComponentStartupParameters, InferenceExperimentDataStorageConfig, InferenceExperimentSchedule, InferenceExperimentType, InputConfig, JobType, JupyterServerAppSettings, KernelGatewayAppSettings, ModelDeployConfig, ModelInfrastructureConfig, MonitoringNetworkConfig, MonitoringOutputConfig, MonitoringResources, MonitoringStoppingCondition, NeoVpcConfig, NetworkConfig, OfflineStoreConfig, OnlineStoreConfig, OutputConfig, ProcessingInstanceType, ProcessingS3UploadMode, Processor, ProductionVariant, ProductionVariantAcceleratorType, ProductionVariantManagedInstanceScaling, ProductionVariantRoutingConfig, ProductionVariantServerlessConfig, RetryStrategy, ShadowModeConfig, TagPropagation, ThroughputMode, UserSettings, VendorGuidance } from "./models_1";
+import { DataCaptureConfig, DataQualityAppSpecification, DataQualityBaselineConfig, DataQualityJobInput, DefaultSpaceSettings, DeploymentConfig, DeviceSelectionConfig, DomainSettings, EdgeDeploymentConfig, EdgeDeploymentModelConfig, EdgeOutputConfig, EdgePresetDeploymentType, EndpointInfo, ExplainerConfig, FeatureDefinition, FeatureType, FlowDefinitionOutputConfig, HubS3StorageConfig, HumanLoopActivationConfig, HumanLoopConfig, HumanLoopRequestSource, HyperParameterTrainingJobDefinition, HyperParameterTuningJobConfig, HyperParameterTuningJobWarmStartConfig, InferenceComponentComputeResourceRequirements, InferenceComponentStartupParameters, InferenceExperimentDataStorageConfig, InferenceExperimentSchedule, InferenceExperimentType, InputConfig, JobType, JupyterServerAppSettings, KernelGatewayAppSettings, ModelDeployConfig, ModelInfrastructureConfig, MonitoringNetworkConfig, MonitoringOutputConfig, MonitoringResources, MonitoringStoppingCondition, NeoVpcConfig, NetworkConfig, OfflineStoreConfig, OnlineStoreConfig, OptimizationConfig, OptimizationJobDeploymentInstanceType, OptimizationJobModelSource, OptimizationJobOutputConfig, OptimizationVpcConfig, OutputConfig, ProcessingInstanceType, ProcessingS3UploadMode, Processor, ProductionVariant, ProductionVariantAcceleratorType, ProductionVariantManagedInstanceScaling, ProductionVariantRoutingConfig, ProductionVariantServerlessConfig, RetryStrategy, ShadowModeConfig, TagPropagation, ThroughputMode, UserSettings, VendorGuidance } from "./models_1";
+/**
+ * @public
+ */
+export interface CreateOptimizationJobRequest {
+    /**
+     * <p>A custom name for the new optimization job.</p>
+     * @public
+     */
+    OptimizationJobName: string | undefined;
+    /**
+     * <p>The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker to perform tasks on your behalf. </p>
+     *          <p>During model optimization, Amazon SageMaker needs your permission to:</p>
+     *          <ul>
+     *             <li>
+     *                <p>Read input data from an S3 bucket</p>
+     *             </li>
+     *             <li>
+     *                <p>Write model artifacts to an S3 bucket</p>
+     *             </li>
+     *             <li>
+     *                <p>Write logs to Amazon CloudWatch Logs</p>
+     *             </li>
+     *             <li>
+     *                <p>Publish metrics to Amazon CloudWatch</p>
+     *             </li>
+     *          </ul>
+     *          <p>You grant permissions for all of these tasks to an IAM role. To pass this
+     *          role to Amazon SageMaker, the caller of this API must have the
+     *             <code>iam:PassRole</code> permission. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-roles.html">Amazon SageMaker Roles.</a>
+     *          </p>
+     * @public
+     */
+    RoleArn: string | undefined;
+    /**
+     * <p>The location of the source model to optimize with an optimization job.</p>
+     * @public
+     */
+    ModelSource: OptimizationJobModelSource | undefined;
+    /**
+     * <p>The type of instance that hosts the optimized model that you create with the optimization job.</p>
+     * @public
+     */
+    DeploymentInstanceType: OptimizationJobDeploymentInstanceType | undefined;
+    /**
+     * <p>The environment variables to set in the model container.</p>
+     * @public
+     */
+    OptimizationEnvironment?: Record<string, string> | undefined;
+    /**
+     * <p>Settings for each of the optimization techniques that the job applies.</p>
+     * @public
+     */
+    OptimizationConfigs: OptimizationConfig[] | undefined;
+    /**
+     * <p>Details for where to store the optimized model that you create with the optimization job.</p>
+     * @public
+     */
+    OutputConfig: OptimizationJobOutputConfig | undefined;
+    /**
+     * <p>Specifies a limit to how long a job can run. When the job reaches the time limit, SageMaker
+     *             ends the job. Use this API to cap costs.</p>
+     *          <p>To stop a training job, SageMaker sends the algorithm the <code>SIGTERM</code> signal,
+     *             which delays job termination for 120 seconds. Algorithms can use this 120-second window
+     *             to save the model artifacts, so the results of training are not lost. </p>
+     *          <p>The training algorithms provided by SageMaker automatically save the intermediate results
+     *             of a model training job when possible. This attempt to save artifacts is only a best
+     *             effort case as model might not be in a state from which it can be saved. For example, if
+     *             training has just started, the model might not be ready to save. When saved, this
+     *             intermediate data is a valid model artifact. You can use it to create a model with
+     *                 <code>CreateModel</code>.</p>
+     *          <note>
+     *             <p>The Neural Topic Model (NTM) currently does not support saving intermediate model
+     *                 artifacts. When training NTMs, make sure that the maximum runtime is sufficient for
+     *                 the training job to complete.</p>
+     *          </note>
+     * @public
+     */
+    StoppingCondition: StoppingCondition | undefined;
+    /**
+     * <p>A list of key-value pairs associated with the optimization job. For more information,
+     *          see <a href="https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html">Tagging Amazon Web Services resources</a> in the <i>Amazon Web Services General Reference
+     *             Guide</i>.</p>
+     * @public
+     */
+    Tags?: Tag[] | undefined;
+    /**
+     * <p>A VPC in Amazon VPC that your optimized model has access to.</p>
+     * @public
+     */
+    VpcConfig?: OptimizationVpcConfig | undefined;
+}
 /**
  * @public
  */
@@ -7349,11 +7440,16 @@ export interface InferenceComponentSpecificationSummary {
      */
     StartupParameters?: InferenceComponentStartupParameters | undefined;
     /**
-     * <p>The compute resources allocated to run the model assigned
-     *          to the inference component.</p>
+     * <p>The compute resources allocated to run the model, plus any
+     *          adapter models, that you assign to the inference component.</p>
      * @public
      */
     ComputeResourceRequirements?: InferenceComponentComputeResourceRequirements | undefined;
+    /**
+     * <p>The name of the base inference component that contains this inference component.</p>
+     * @public
+     */
+    BaseInferenceComponentName?: string | undefined;
 }
 /**
  * @public
@@ -7898,24 +7994,6 @@ export interface InferenceRecommendation {
      */
     InvocationStartTime?: Date | undefined;
 }
-/**
- * @public
- * @enum
- */
-export declare const RecommendationJobStatus: {
-    readonly COMPLETED: "COMPLETED";
-    readonly DELETED: "DELETED";
-    readonly DELETING: "DELETING";
-    readonly FAILED: "FAILED";
-    readonly IN_PROGRESS: "IN_PROGRESS";
-    readonly PENDING: "PENDING";
-    readonly STOPPED: "STOPPED";
-    readonly STOPPING: "STOPPING";
-};
-/**
- * @public
- */
-export type RecommendationJobStatus = (typeof RecommendationJobStatus)[keyof typeof RecommendationJobStatus];
 /**
  * @internal
  */

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

@@ -1,6 +1,24 @@
 import { ActionSummary, AdditionalInferenceSpecificationDefinition, AgentVersion, AlgorithmSortBy, AlgorithmSpecification, AlgorithmSummary, AmazonQSettings, AppDetails, AppImageConfigDetails, AppImageConfigSortKey, AppSortKey, AppSpecification, ArtifactSummary, AssociationEdgeType, AssociationSummary, AutoMLCandidate, AutoMLJobStatus, AutoMLJobSummary, AutoMLSortBy, AutoMLSortOrder, BatchDataCaptureConfig, BatchStrategy, CandidateSortBy, CandidateStatus, Channel, CheckpointConfig, ClusterNodeSummary, ClusterSortBy, ClusterSummary, CodeRepositorySortBy, CodeRepositorySortOrder, CodeRepositorySummary, CognitoConfig, CompilationJobStatus, CompilationJobSummary, ContainerDefinition, ContextSummary, InferenceSpecification, MetadataProperties, ModelApprovalStatus, ModelPackageStatus, OutputDataConfig, OutputParameter, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TransformInput, TransformOutput, TransformResources, UserContext, VpcConfig } from "./models_0";
 import { _InstanceType, DirectInternetAccess, DockerSettings, DriftCheckBaselines, EdgeOutputConfig, ExecutionRoleIdentityConfig, FeatureDefinition, FeatureType, HumanTaskConfig, HyperParameterTrainingJobDefinition, HyperParameterTuningJobConfig, HyperParameterTuningJobStrategyType, HyperParameterTuningJobWarmStartConfig, InferenceExecutionConfig, InferenceExperimentSchedule, InferenceExperimentType, InstanceMetadataServiceConfiguration, LabelingJobAlgorithmsConfig, LabelingJobInputConfig, LabelingJobOutputConfig, LabelingJobStoppingConditions, ModelBiasAppSpecification, ModelBiasBaselineConfig, ModelBiasJobInput, ModelCardExportOutputConfig, ModelCardSecurityConfig, ModelCardStatus, ModelExplainabilityAppSpecification, ModelExplainabilityBaselineConfig, ModelExplainabilityJobInput, ModelLifeCycle, ModelMetrics, ModelPackageModelCard, ModelPackageSecurityConfig, ModelPackageValidationSpecification, ModelQualityAppSpecification, ModelQualityBaselineConfig, ModelQualityJobInput, MonitoringNetworkConfig, MonitoringOutputConfig, MonitoringResources, MonitoringScheduleConfig, MonitoringStoppingCondition, MonitoringType, NetworkConfig, NotebookInstanceAcceleratorType, NotebookInstanceLifecycleHook, OfflineStoreConfig, OnlineStoreConfig, OptimizationConfig, OptimizationJobDeploymentInstanceType, OptimizationJobModelSource, OptimizationJobOutputConfig, OptimizationVpcConfig, RecommendationJobInputConfig, RecommendationJobStoppingConditions, RecommendationJobType, ResourceLimits, RetryStrategy, RootAccess, SkipModelValidation, SourceAlgorithmSpecification, TrackingServerSize, UserSettings } from "./models_1";
-import { CustomizedMetricSpecification, DataCaptureConfigSummary, DataProcessing, DebugHookConfig, DebugRuleConfiguration, DebugRuleEvaluationStatus, DeploymentRecommendation, DomainStatus, EdgePackagingJobStatus, EndpointOutputConfiguration, EndpointPerformance, EndpointStatus, ExperimentConfig, ExperimentSource, FeatureGroupStatus, FeatureParameter, FlowDefinitionStatus, HubContentStatus, HubContentSupportStatus, HubContentType, HubStatus, HyperParameterTrainingJobSummary, HyperParameterTuningJobCompletionDetails, HyperParameterTuningJobConsumedResources, HyperParameterTuningJobStatus, ImageStatus, ImageVersionStatus, InferenceComponentStatus, InferenceExperimentStatus, InferenceMetrics, InferenceRecommendation, InfraCheckConfig, LastUpdateStatus, MemberDefinition, ModelArtifacts, ModelClientConfig, ModelConfiguration, NotificationConfiguration, ObjectiveStatusCounters, OfflineStoreStatus, OfflineStoreStatusValue, OwnershipSettings, ParallelismConfiguration, ProcessingInput, ProcessingOutputConfig, ProcessingResources, ProcessingStoppingCondition, ProductionVariantSummary, ProfilerConfig, ProfilerRuleConfiguration, RecommendationJobStatus, RecommendationMetrics, RemoteDebugConfig, RuleEvaluationStatus, ServiceCatalogProvisioningDetails, SourceIpConfig, SpaceSettings, SpaceSharingSettings, StudioLifecycleConfigAppType, TensorBoardOutputConfig, TrainingJobStatus, TrainingJobStatusCounters, TrialComponentArtifact, TrialComponentParameterValue, TrialComponentStatus, WorkerAccessConfiguration } from "./models_2";
+import { CustomizedMetricSpecification, DataCaptureConfigSummary, DataProcessing, DebugHookConfig, DebugRuleConfiguration, DebugRuleEvaluationStatus, DeploymentRecommendation, DomainStatus, EdgePackagingJobStatus, EndpointOutputConfiguration, EndpointPerformance, EndpointStatus, ExperimentConfig, ExperimentSource, FeatureGroupStatus, FeatureParameter, FlowDefinitionStatus, HubContentStatus, HubContentSupportStatus, HubContentType, HubStatus, HyperParameterTrainingJobSummary, HyperParameterTuningJobCompletionDetails, HyperParameterTuningJobConsumedResources, HyperParameterTuningJobStatus, ImageStatus, ImageVersionStatus, InferenceComponentStatus, InferenceExperimentStatus, InferenceMetrics, InferenceRecommendation, InfraCheckConfig, LastUpdateStatus, MemberDefinition, ModelArtifacts, ModelClientConfig, ModelConfiguration, NotificationConfiguration, ObjectiveStatusCounters, OfflineStoreStatus, OfflineStoreStatusValue, OwnershipSettings, ParallelismConfiguration, ProcessingInput, ProcessingOutputConfig, ProcessingResources, ProcessingStoppingCondition, ProductionVariantSummary, ProfilerConfig, ProfilerRuleConfiguration, RecommendationMetrics, RemoteDebugConfig, RuleEvaluationStatus, ServiceCatalogProvisioningDetails, SourceIpConfig, SpaceSettings, SpaceSharingSettings, StudioLifecycleConfigAppType, TensorBoardOutputConfig, TrainingJobStatus, TrainingJobStatusCounters, TrialComponentArtifact, TrialComponentParameterValue, TrialComponentStatus, WorkerAccessConfiguration } from "./models_2";
+/**
+ * @public
+ * @enum
+ */
+export declare const RecommendationJobStatus: {
+    readonly COMPLETED: "COMPLETED";
+    readonly DELETED: "DELETED";
+    readonly DELETING: "DELETING";
+    readonly FAILED: "FAILED";
+    readonly IN_PROGRESS: "IN_PROGRESS";
+    readonly PENDING: "PENDING";
+    readonly STOPPED: "STOPPED";
+    readonly STOPPING: "STOPPING";
+};
+/**
+ * @public
+ */
+export type RecommendationJobStatus = (typeof RecommendationJobStatus)[keyof typeof RecommendationJobStatus];
 /**
  * @public
  */
@@ -10121,22 +10139,6 @@ export interface ListLineageGroupsRequest {
      */
     MaxResults?: number | undefined;
 }
-/**
- * @public
- */
-export interface ListLineageGroupsResponse {
-    /**
-     * <p>A list of lineage groups and their properties.</p>
-     * @public
-     */
-    LineageGroupSummaries?: LineageGroupSummary[] | undefined;
-    /**
-     * <p>If the response is truncated, SageMaker returns this token. To retrieve the next set of
-     *          algorithms, use it in the subsequent request.</p>
-     * @public
-     */
-    NextToken?: string | undefined;
-}
 /**
  * @internal
  */

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

@@ -1,7 +1,23 @@
 import { ActionStatus, AdditionalInferenceSpecificationDefinition, AlgorithmSpecification, AppNetworkAccessType, AppSecurityGroupManagement, AppSpecification, AppType, AutoMLJobStepMetadata, BatchDataCaptureConfig, BatchStrategy, BatchTransformInput, CacheHitResult, CallbackStepMetadata, Channel, CheckpointConfig, ClarifyCheckStepMetadata, ClusterInstanceGroupSpecification, ClusterNodeRecovery, CodeEditorAppImageConfig, ConditionStepMetadata, ContainerDefinition, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, MetadataProperties, ModelApprovalStatus, ModelPackageStatus, OutputDataConfig, OutputParameter, ResourceConfig, StoppingCondition, Tag, TransformInput, TransformOutput, TransformResources, UserContext, VpcConfig } from "./models_0";
 import { _InstanceType, DefaultSpaceSettings, DeploymentConfig, DriftCheckBaselines, EdgeOutputConfig, FeatureDefinition, InferenceComponentRuntimeConfig, InferenceComponentSpecification, InferenceExecutionConfig, InferenceExperimentDataStorageConfig, InferenceExperimentSchedule, InstanceMetadataServiceConfiguration, JobType, ModelCardSecurityConfig, ModelCardStatus, ModelLifeCycle, ModelMetrics, ModelPackageModelCard, ModelPackageSecurityConfig, ModelPackageValidationSpecification, ModelVariantConfig, MonitoringScheduleConfig, MonitoringType, NetworkConfig, NotebookInstanceAcceleratorType, NotebookInstanceLifecycleHook, OptimizationJobDeploymentInstanceType, Processor, RetryStrategy, RootAccess, ShadowModeConfig, SkipModelValidation, SourceAlgorithmSpecification, TagPropagation, ThroughputMode, TrackingServerSize, TtlDuration, UiTemplate, UserSettings, VendorGuidance } from "./models_1";
 import { CrossAccountFilterOption, DataProcessing, DebugHookConfig, DebugRuleConfiguration, DebugRuleEvaluationStatus, DeploymentRecommendation, EndpointStatus, ExperimentConfig, FeatureParameter, HyperParameterTrainingJobSummary, ModelArtifacts, ModelClientConfig, ParallelismConfiguration, PipelineDefinitionS3Location, ProcessingInput, ProcessingOutputConfig, ProcessingResources, ProcessingStoppingCondition, ProfilerConfig, ProfilerRuleConfiguration, ProvisioningParameter, ServiceCatalogProvisioningDetails, SharingType, SpaceSettings, SpaceStorageSettings, StudioLifecycleConfigAppType, TensorBoardOutputConfig, TrainingJobStatus, TrialComponentArtifact, TrialComponentParameterValue, TrialComponentStatus } from "./models_2";
-import { DesiredWeightAndCapacity, Device, DeviceDeploymentSummary, Direction, DomainSettingsForUpdate, Edge, EMRStepMetadata, Endpoint, EndpointConfigStepMetadata, EndpointStepMetadata, ExecutionStatus, Experiment, FailStepMetadata, FeatureGroup, FeatureMetadata, Filter, GitConfigForUpdate, HyperParameterTuningJobSearchEntity, InferenceExperimentStopDesiredState, IsTrackingServerActive, LambdaStepMetadata, LineageType, MetricData, ModelCardExportJobStatus, ModelPackageGroupStatus, ModelPackageStatusDetails, MonitoringExecutionSummary, MonitoringJobDefinitionSortKey, MonitoringJobDefinitionSummary, NotebookInstanceStatus, OptimizationJobStatus, OrderKey, PipelineExecutionStatus, PipelineExperimentConfig, PipelineStatus, ProcessingJobStatus, ProjectStatus, ScheduleStatus, SecondaryStatus, SecondaryStatusTransition, SelectiveExecutionConfig, ServiceCatalogProvisionedProductDetails, SortBy, SortOrder, SpaceStatus, SubscribedWorkteam, TrackingServerStatus, TransformJobStatus, TrialComponentMetricSummary, TrialComponentSource, TrialSource, UserProfileStatus, WarmPoolResourceStatus, WarmPoolStatus, Workforce, Workteam } from "./models_3";
+import { DesiredWeightAndCapacity, Device, DeviceDeploymentSummary, Direction, DomainSettingsForUpdate, Edge, EMRStepMetadata, Endpoint, EndpointConfigStepMetadata, EndpointStepMetadata, ExecutionStatus, Experiment, FailStepMetadata, FeatureGroup, FeatureMetadata, Filter, GitConfigForUpdate, HyperParameterTuningJobSearchEntity, InferenceExperimentStopDesiredState, IsTrackingServerActive, LambdaStepMetadata, LineageGroupSummary, LineageType, MetricData, ModelCardExportJobStatus, ModelPackageGroupStatus, ModelPackageStatusDetails, MonitoringExecutionSummary, MonitoringJobDefinitionSortKey, MonitoringJobDefinitionSummary, NotebookInstanceStatus, OptimizationJobStatus, OrderKey, PipelineExecutionStatus, PipelineExperimentConfig, PipelineStatus, ProcessingJobStatus, ProjectStatus, ScheduleStatus, SecondaryStatus, SecondaryStatusTransition, SelectiveExecutionConfig, ServiceCatalogProvisionedProductDetails, SortBy, SortOrder, SpaceStatus, SubscribedWorkteam, TrackingServerStatus, TransformJobStatus, TrialComponentMetricSummary, TrialComponentSource, TrialSource, UserProfileStatus, WarmPoolResourceStatus, WarmPoolStatus, Workforce, Workteam } from "./models_3";
+/**
+ * @public
+ */
+export interface ListLineageGroupsResponse {
+    /**
+     * <p>A list of lineage groups and their properties.</p>
+     * @public
+     */
+    LineageGroupSummaries?: LineageGroupSummary[] | undefined;
+    /**
+     * <p>If the response is truncated, SageMaker returns this token. To retrieve the next set of
+     *          algorithms, use it in the subsequent request.</p>
+     * @public
+     */
+    NextToken?: string | undefined;
+}
 /**
  * @public
  * @enum
@@ -8979,16 +8995,6 @@ export interface UpdateTrialComponentRequest {
      */
     OutputArtifactsToRemove?: string[] | undefined;
 }
-/**
- * @public
- */
-export interface UpdateTrialComponentResponse {
-    /**
-     * <p>The Amazon Resource Name (ARN) of the trial component.</p>
-     * @public
-     */
-    TrialComponentArn?: string | undefined;
-}
 /**
  * @internal
  */

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

@@ -3,6 +3,16 @@ import { UserSettings } from "./models_1";
 import { CrossAccountFilterOption, MemberDefinition, NotificationConfiguration, OidcConfig, SourceIpConfig, WorkerAccessConfiguration, WorkforceVpcConfigRequest } from "./models_2";
 import { Filter, ResourceType, Workforce, Workteam } from "./models_3";
 import { NestedFilters, SearchSortOrder, VisibilityConditions } from "./models_4";
+/**
+ * @public
+ */
+export interface UpdateTrialComponentResponse {
+    /**
+     * <p>The Amazon Resource Name (ARN) of the trial component.</p>
+     * @public
+     */
+    TrialComponentArn?: string | undefined;
+}
 /**
  * @public
  */

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

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

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

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

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

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

package/dist-types/ts3.4/models/models_0.d.ts

@@ -197,6 +197,14 @@ export declare const ProductionVariantInstanceType: {
   readonly ML_G5_4XLARGE: "ml.g5.4xlarge";
   readonly ML_G5_8XLARGE: "ml.g5.8xlarge";
   readonly ML_G5_XLARGE: "ml.g5.xlarge";
+  readonly ML_G6E_12XLARGE: "ml.g6e.12xlarge";
+  readonly ML_G6E_16XLARGE: "ml.g6e.16xlarge";
+  readonly ML_G6E_24XLARGE: "ml.g6e.24xlarge";
+  readonly ML_G6E_2XLARGE: "ml.g6e.2xlarge";
+  readonly ML_G6E_48XLARGE: "ml.g6e.48xlarge";
+  readonly ML_G6E_4XLARGE: "ml.g6e.4xlarge";
+  readonly ML_G6E_8XLARGE: "ml.g6e.8xlarge";
+  readonly ML_G6E_XLARGE: "ml.g6e.xlarge";
   readonly ML_G6_12XLARGE: "ml.g6.12xlarge";
   readonly ML_G6_16XLARGE: "ml.g6.16xlarge";
   readonly ML_G6_24XLARGE: "ml.g6.24xlarge";
@@ -244,6 +252,15 @@ export declare const ProductionVariantInstanceType: {
   readonly ML_M6G_8XLARGE: "ml.m6g.8xlarge";
   readonly ML_M6G_LARGE: "ml.m6g.large";
   readonly ML_M6G_XLARGE: "ml.m6g.xlarge";
+  readonly ML_M6I_12XLARGE: "ml.m6i.12xlarge";
+  readonly ML_M6I_16XLARGE: "ml.m6i.16xlarge";
+  readonly ML_M6I_24XLARGE: "ml.m6i.24xlarge";
+  readonly ML_M6I_2XLARGE: "ml.m6i.2xlarge";
+  readonly ML_M6I_32XLARGE: "ml.m6i.32xlarge";
+  readonly ML_M6I_4XLARGE: "ml.m6i.4xlarge";
+  readonly ML_M6I_8XLARGE: "ml.m6i.8xlarge";
+  readonly ML_M6I_LARGE: "ml.m6i.large";
+  readonly ML_M6I_XLARGE: "ml.m6i.xlarge";
   readonly ML_M7I_12XLARGE: "ml.m7i.12xlarge";
   readonly ML_M7I_16XLARGE: "ml.m7i.16xlarge";
   readonly ML_M7I_24XLARGE: "ml.m7i.24xlarge";
@@ -261,6 +278,7 @@ export declare const ProductionVariantInstanceType: {
   readonly ML_P3_8XLARGE: "ml.p3.8xlarge";
   readonly ML_P4DE_24XLARGE: "ml.p4de.24xlarge";
   readonly ML_P4D_24XLARGE: "ml.p4d.24xlarge";
+  readonly ML_P5E_48XLARGE: "ml.p5e.48xlarge";
   readonly ML_P5_48XLARGE: "ml.p5.48xlarge";
   readonly ML_R5D_12XLARGE: "ml.r5d.12xlarge";
   readonly ML_R5D_24XLARGE: "ml.r5d.24xlarge";
@@ -288,6 +306,15 @@ export declare const ProductionVariantInstanceType: {
   readonly ML_R6G_8XLARGE: "ml.r6g.8xlarge";
   readonly ML_R6G_LARGE: "ml.r6g.large";
   readonly ML_R6G_XLARGE: "ml.r6g.xlarge";
+  readonly ML_R6I_12XLARGE: "ml.r6i.12xlarge";
+  readonly ML_R6I_16XLARGE: "ml.r6i.16xlarge";
+  readonly ML_R6I_24XLARGE: "ml.r6i.24xlarge";
+  readonly ML_R6I_2XLARGE: "ml.r6i.2xlarge";
+  readonly ML_R6I_32XLARGE: "ml.r6i.32xlarge";
+  readonly ML_R6I_4XLARGE: "ml.r6i.4xlarge";
+  readonly ML_R6I_8XLARGE: "ml.r6i.8xlarge";
+  readonly ML_R6I_LARGE: "ml.r6i.large";
+  readonly ML_R6I_XLARGE: "ml.r6i.xlarge";
   readonly ML_R7I_12XLARGE: "ml.r7i.12xlarge";
   readonly ML_R7I_16XLARGE: "ml.r7i.16xlarge";
   readonly ML_R7I_24XLARGE: "ml.r7i.24xlarge";
@@ -304,6 +331,7 @@ export declare const ProductionVariantInstanceType: {
   readonly ML_TRN1N_32XLARGE: "ml.trn1n.32xlarge";
   readonly ML_TRN1_2XLARGE: "ml.trn1.2xlarge";
   readonly ML_TRN1_32XLARGE: "ml.trn1.32xlarge";
+  readonly ML_TRN2_48XLARGE: "ml.trn2.48xlarge";
 };
 export type ProductionVariantInstanceType =
   (typeof ProductionVariantInstanceType)[keyof typeof ProductionVariantInstanceType];
@@ -2207,6 +2235,7 @@ export interface ClusterInstanceGroupDetails {
   ThreadsPerCore?: number | undefined;
   InstanceStorageConfigs?: ClusterInstanceStorageConfig[] | undefined;
   OnStartDeepHealthChecks?: DeepHealthCheckType[] | undefined;
+  OverrideVpcConfig?: VpcConfig | undefined;
 }
 export interface ClusterInstanceGroupSpecification {
   InstanceCount: number | undefined;
@@ -2217,6 +2246,7 @@ export interface ClusterInstanceGroupSpecification {
   ThreadsPerCore?: number | undefined;
   InstanceStorageConfigs?: ClusterInstanceStorageConfig[] | undefined;
   OnStartDeepHealthChecks?: DeepHealthCheckType[] | undefined;
+  OverrideVpcConfig?: VpcConfig | undefined;
 }
 export interface ClusterInstancePlacement {
   AvailabilityZone?: string | undefined;
@@ -2243,6 +2273,7 @@ export interface ClusterNodeDetails {
   InstanceType?: ClusterInstanceType | undefined;
   LaunchTime?: Date | undefined;
   LifeCycleConfig?: ClusterLifeCycleConfig | undefined;
+  OverrideVpcConfig?: VpcConfig | undefined;
   ThreadsPerCore?: number | undefined;
   InstanceStorageConfigs?: ClusterInstanceStorageConfig[] | undefined;
   PrivatePrimaryIp?: string | undefined;

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

@@ -1166,16 +1166,17 @@ export interface InferenceComponentSpecification {
   ModelName?: string | undefined;
   Container?: InferenceComponentContainerSpecification | undefined;
   StartupParameters?: InferenceComponentStartupParameters | undefined;
-  ComputeResourceRequirements:
+  ComputeResourceRequirements?:
     | InferenceComponentComputeResourceRequirements
     | undefined;
+  BaseInferenceComponentName?: string | undefined;
 }
 export interface CreateInferenceComponentInput {
   InferenceComponentName: string | undefined;
   EndpointName: string | undefined;
-  VariantName: string | undefined;
+  VariantName?: string | undefined;
   Specification: InferenceComponentSpecification | undefined;
-  RuntimeConfig: InferenceComponentRuntimeConfig | undefined;
+  RuntimeConfig?: InferenceComponentRuntimeConfig | undefined;
   Tags?: Tag[] | undefined;
 }
 export interface CreateInferenceComponentOutput {
@@ -2056,29 +2057,44 @@ export interface ModelQuantizationConfig {
   Image?: string | undefined;
   OverrideEnvironment?: Record<string, string> | undefined;
 }
+export interface ModelShardingConfig {
+  Image?: string | undefined;
+  OverrideEnvironment?: Record<string, string> | undefined;
+}
 export type OptimizationConfig =
   | OptimizationConfig.ModelCompilationConfigMember
   | OptimizationConfig.ModelQuantizationConfigMember
+  | OptimizationConfig.ModelShardingConfigMember
   | OptimizationConfig.$UnknownMember;
 export declare namespace OptimizationConfig {
   interface ModelQuantizationConfigMember {
     ModelQuantizationConfig: ModelQuantizationConfig;
     ModelCompilationConfig?: never;
+    ModelShardingConfig?: never;
     $unknown?: never;
   }
   interface ModelCompilationConfigMember {
     ModelQuantizationConfig?: never;
     ModelCompilationConfig: ModelCompilationConfig;
+    ModelShardingConfig?: never;
+    $unknown?: never;
+  }
+  interface ModelShardingConfigMember {
+    ModelQuantizationConfig?: never;
+    ModelCompilationConfig?: never;
+    ModelShardingConfig: ModelShardingConfig;
     $unknown?: never;
   }
   interface $UnknownMember {
     ModelQuantizationConfig?: never;
     ModelCompilationConfig?: never;
+    ModelShardingConfig?: never;
     $unknown: [string, any];
   }
   interface Visitor<T> {
     ModelQuantizationConfig: (value: ModelQuantizationConfig) => T;
     ModelCompilationConfig: (value: ModelCompilationConfig) => T;
+    ModelShardingConfig: (value: ModelShardingConfig) => T;
     _: (name: string, value: any) => T;
   }
   const visit: <T>(value: OptimizationConfig, visitor: Visitor<T>) => T;
@@ -2091,18 +2107,6 @@ export interface OptimizationVpcConfig {
   SecurityGroupIds: string[] | undefined;
   Subnets: string[] | undefined;
 }
-export interface CreateOptimizationJobRequest {
-  OptimizationJobName: string | undefined;
-  RoleArn: string | undefined;
-  ModelSource: OptimizationJobModelSource | undefined;
-  DeploymentInstanceType: OptimizationJobDeploymentInstanceType | undefined;
-  OptimizationEnvironment?: Record<string, string> | undefined;
-  OptimizationConfigs: OptimizationConfig[] | undefined;
-  OutputConfig: OptimizationJobOutputConfig | undefined;
-  StoppingCondition: StoppingCondition | undefined;
-  Tags?: Tag[] | undefined;
-  VpcConfig?: OptimizationVpcConfig | undefined;
-}
 export declare const CreateModelCardRequestFilterSensitiveLog: (
   obj: CreateModelCardRequest
 ) => any;

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

@@ -116,6 +116,11 @@ import {
   NetworkConfig,
   OfflineStoreConfig,
   OnlineStoreConfig,
+  OptimizationConfig,
+  OptimizationJobDeploymentInstanceType,
+  OptimizationJobModelSource,
+  OptimizationJobOutputConfig,
+  OptimizationVpcConfig,
   OutputConfig,
   ProcessingInstanceType,
   ProcessingS3UploadMode,
@@ -132,6 +137,18 @@ import {
   UserSettings,
   VendorGuidance,
 } from "./models_1";
+export interface CreateOptimizationJobRequest {
+  OptimizationJobName: string | undefined;
+  RoleArn: string | undefined;
+  ModelSource: OptimizationJobModelSource | undefined;
+  DeploymentInstanceType: OptimizationJobDeploymentInstanceType | undefined;
+  OptimizationEnvironment?: Record<string, string> | undefined;
+  OptimizationConfigs: OptimizationConfig[] | undefined;
+  OutputConfig: OptimizationJobOutputConfig | undefined;
+  StoppingCondition: StoppingCondition | undefined;
+  Tags?: Tag[] | undefined;
+  VpcConfig?: OptimizationVpcConfig | undefined;
+}
 export interface CreateOptimizationJobResponse {
   OptimizationJobArn: string | undefined;
 }
@@ -1856,6 +1873,7 @@ export interface InferenceComponentSpecificationSummary {
   ComputeResourceRequirements?:
     | InferenceComponentComputeResourceRequirements
     | undefined;
+  BaseInferenceComponentName?: string | undefined;
 }
 export interface DescribeInferenceComponentOutput {
   InferenceComponentName: string | undefined;
@@ -1969,18 +1987,6 @@ export interface InferenceRecommendation {
   InvocationEndTime?: Date | undefined;
   InvocationStartTime?: Date | undefined;
 }
-export declare const RecommendationJobStatus: {
-  readonly COMPLETED: "COMPLETED";
-  readonly DELETED: "DELETED";
-  readonly DELETING: "DELETING";
-  readonly FAILED: "FAILED";
-  readonly IN_PROGRESS: "IN_PROGRESS";
-  readonly PENDING: "PENDING";
-  readonly STOPPED: "STOPPED";
-  readonly STOPPING: "STOPPING";
-};
-export type RecommendationJobStatus =
-  (typeof RecommendationJobStatus)[keyof typeof RecommendationJobStatus];
 export declare const OidcConfigFilterSensitiveLog: (obj: OidcConfig) => any;
 export declare const CreateWorkforceRequestFilterSensitiveLog: (
   obj: CreateWorkforceRequest

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

@@ -169,7 +169,6 @@ import {
   ProductionVariantSummary,
   ProfilerConfig,
   ProfilerRuleConfiguration,
-  RecommendationJobStatus,
   RecommendationMetrics,
   RemoteDebugConfig,
   RuleEvaluationStatus,
@@ -186,6 +185,18 @@ import {
   TrialComponentStatus,
   WorkerAccessConfiguration,
 } from "./models_2";
+export declare const RecommendationJobStatus: {
+  readonly COMPLETED: "COMPLETED";
+  readonly DELETED: "DELETED";
+  readonly DELETING: "DELETING";
+  readonly FAILED: "FAILED";
+  readonly IN_PROGRESS: "IN_PROGRESS";
+  readonly PENDING: "PENDING";
+  readonly STOPPED: "STOPPED";
+  readonly STOPPING: "STOPPING";
+};
+export type RecommendationJobStatus =
+  (typeof RecommendationJobStatus)[keyof typeof RecommendationJobStatus];
 export interface DescribeInferenceRecommendationsJobResponse {
   JobName: string | undefined;
   JobDescription?: string | undefined;
@@ -2504,10 +2515,6 @@ export interface ListLineageGroupsRequest {
   NextToken?: string | undefined;
   MaxResults?: number | undefined;
 }
-export interface ListLineageGroupsResponse {
-  LineageGroupSummaries?: LineageGroupSummary[] | undefined;
-  NextToken?: string | undefined;
-}
 export declare const DescribeModelCardResponseFilterSensitiveLog: (
   obj: DescribeModelCardResponse
 ) => any;

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

@@ -134,6 +134,7 @@ import {
   InferenceExperimentStopDesiredState,
   IsTrackingServerActive,
   LambdaStepMetadata,
+  LineageGroupSummary,
   LineageType,
   MetricData,
   ModelCardExportJobStatus,
@@ -170,6 +171,10 @@ import {
   Workforce,
   Workteam,
 } from "./models_3";
+export interface ListLineageGroupsResponse {
+  LineageGroupSummaries?: LineageGroupSummary[] | undefined;
+  NextToken?: string | undefined;
+}
 export declare const SortTrackingServerBy: {
   readonly CREATION_TIME: "CreationTime";
   readonly NAME: "Name";
@@ -2120,9 +2125,6 @@ export interface UpdateTrialComponentRequest {
   OutputArtifacts?: Record<string, TrialComponentArtifact> | undefined;
   OutputArtifactsToRemove?: string[] | undefined;
 }
-export interface UpdateTrialComponentResponse {
-  TrialComponentArn?: string | undefined;
-}
 export declare const ModelCardFilterSensitiveLog: (obj: ModelCard) => any;
 export declare const ModelPackageFilterSensitiveLog: (obj: ModelPackage) => any;
 export declare const SearchRecordFilterSensitiveLog: (obj: SearchRecord) => any;

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

@@ -15,6 +15,9 @@ import {
   SearchSortOrder,
   VisibilityConditions,
 } from "./models_4";
+export interface UpdateTrialComponentResponse {
+  TrialComponentArn?: string | undefined;
+}
 export interface UpdateUserProfileRequest {
   DomainId: string | undefined;
   UserProfileName: string | undefined;