@aws-sdk/client-sagemaker 3.1019.0 → 3.1021.0

package/dist-types/auth/httpAuthExtensionConfiguration.d.ts

@@ -1,4 +1,4 @@
-import { type HttpAuthScheme, AwsCredentialIdentity, AwsCredentialIdentityProvider } from "@smithy/types";
+import type { AwsCredentialIdentity, AwsCredentialIdentityProvider, HttpAuthScheme } from "@smithy/types";
 import type { SageMakerHttpAuthSchemeProvider } from "./httpAuthSchemeProvider";
 /**
  * @internal

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

@@ -63,6 +63,11 @@ declare const CreateEndpointConfigCommand_base: {
  *         Status: "ENABLED" || "DISABLED",
  *         MinInstanceCount: Number("int"),
  *         MaxInstanceCount: Number("int"),
+ *         ScaleInPolicy: { // ProductionVariantManagedInstanceScalingScaleInPolicy
+ *           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ *           MaximumStepSize: Number("int"),
+ *           CooldownInMinutes: Number("int"),
+ *         },
  *       },
  *       RoutingConfig: { // ProductionVariantRoutingConfig
  *         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -180,6 +185,11 @@ declare const CreateEndpointConfigCommand_base: {
  *         Status: "ENABLED" || "DISABLED",
  *         MinInstanceCount: Number("int"),
  *         MaxInstanceCount: Number("int"),
+ *         ScaleInPolicy: {
+ *           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ *           MaximumStepSize: Number("int"),
+ *           CooldownInMinutes: Number("int"),
+ *         },
  *       },
  *       RoutingConfig: {
  *         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required

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

@@ -63,6 +63,13 @@ declare const CreateInferenceComponentCommand_base: {
  *     DataCacheConfig: { // InferenceComponentDataCacheConfig
  *       EnableCaching: true || false, // required
  *     },
+ *     SchedulingConfig: { // InferenceComponentSchedulingConfig
+ *       PlacementStrategy: "SPREAD" || "BINPACK", // required
+ *       AvailabilityZoneBalance: { // InferenceComponentAvailabilityZoneBalance
+ *         EnforcementMode: "PERMISSIVE", // required
+ *         MaxImbalance: Number("int"),
+ *       },
+ *     },
  *   },
  *   RuntimeConfig: { // InferenceComponentRuntimeConfig
  *     CopyCount: Number("int"), // required

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

@@ -80,6 +80,11 @@ declare const DescribeEndpointCommand_base: {
  * //         Status: "ENABLED" || "DISABLED",
  * //         MinInstanceCount: Number("int"),
  * //         MaxInstanceCount: Number("int"),
+ * //         ScaleInPolicy: { // ProductionVariantManagedInstanceScalingScaleInPolicy
+ * //           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //           MaximumStepSize: Number("int"),
+ * //           CooldownInMinutes: Number("int"),
+ * //         },
  * //       },
  * //       RoutingConfig: { // ProductionVariantRoutingConfig
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -205,6 +210,11 @@ declare const DescribeEndpointCommand_base: {
  * //           Status: "ENABLED" || "DISABLED",
  * //           MinInstanceCount: Number("int"),
  * //           MaxInstanceCount: Number("int"),
+ * //           ScaleInPolicy: {
+ * //             Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //             MaximumStepSize: Number("int"),
+ * //             CooldownInMinutes: Number("int"),
+ * //           },
  * //         },
  * //         RoutingConfig: {
  * //           RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -245,6 +255,11 @@ declare const DescribeEndpointCommand_base: {
  * //           Status: "ENABLED" || "DISABLED",
  * //           MinInstanceCount: Number("int"),
  * //           MaxInstanceCount: Number("int"),
+ * //           ScaleInPolicy: {
+ * //             Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //             MaximumStepSize: Number("int"),
+ * //             CooldownInMinutes: Number("int"),
+ * //           },
  * //         },
  * //         RoutingConfig: {
  * //           RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -317,6 +332,11 @@ declare const DescribeEndpointCommand_base: {
  * //         Status: "ENABLED" || "DISABLED",
  * //         MinInstanceCount: Number("int"),
  * //         MaxInstanceCount: Number("int"),
+ * //         ScaleInPolicy: {
+ * //           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //           MaximumStepSize: Number("int"),
+ * //           CooldownInMinutes: Number("int"),
+ * //         },
  * //       },
  * //       RoutingConfig: {
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required

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

@@ -69,6 +69,11 @@ declare const DescribeEndpointConfigCommand_base: {
  * //         Status: "ENABLED" || "DISABLED",
  * //         MinInstanceCount: Number("int"),
  * //         MaxInstanceCount: Number("int"),
+ * //         ScaleInPolicy: { // ProductionVariantManagedInstanceScalingScaleInPolicy
+ * //           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //           MaximumStepSize: Number("int"),
+ * //           CooldownInMinutes: Number("int"),
+ * //         },
  * //       },
  * //       RoutingConfig: { // ProductionVariantRoutingConfig
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -181,6 +186,11 @@ declare const DescribeEndpointConfigCommand_base: {
  * //         Status: "ENABLED" || "DISABLED",
  * //         MinInstanceCount: Number("int"),
  * //         MaxInstanceCount: Number("int"),
+ * //         ScaleInPolicy: {
+ * //           Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //           MaximumStepSize: Number("int"),
+ * //           CooldownInMinutes: Number("int"),
+ * //         },
  * //       },
  * //       RoutingConfig: {
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required

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

@@ -75,6 +75,13 @@ declare const DescribeInferenceComponentCommand_base: {
  * //     DataCacheConfig: { // InferenceComponentDataCacheConfigSummary
  * //       EnableCaching: true || false, // required
  * //     },
+ * //     SchedulingConfig: { // InferenceComponentSchedulingConfig
+ * //       PlacementStrategy: "SPREAD" || "BINPACK", // required
+ * //       AvailabilityZoneBalance: { // InferenceComponentAvailabilityZoneBalance
+ * //         EnforcementMode: "PERMISSIVE", // required
+ * //         MaxImbalance: Number("int"),
+ * //       },
+ * //     },
  * //   },
  * //   RuntimeConfig: { // InferenceComponentRuntimeConfigSummary
  * //     DesiredCopyCount: Number("int"),

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

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

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

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

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

@@ -928,6 +928,11 @@ declare const SearchCommand_base: {
  * //               Status: "ENABLED" || "DISABLED",
  * //               MinInstanceCount: Number("int"),
  * //               MaxInstanceCount: Number("int"),
+ * //               ScaleInPolicy: { // ProductionVariantManagedInstanceScalingScaleInPolicy
+ * //                 Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //                 MaximumStepSize: Number("int"),
+ * //                 CooldownInMinutes: Number("int"),
+ * //               },
  * //             },
  * //             RoutingConfig: { // ProductionVariantRoutingConfig
  * //               RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
@@ -1123,6 +1128,11 @@ declare const SearchCommand_base: {
  * //               Status: "ENABLED" || "DISABLED",
  * //               MinInstanceCount: Number("int"),
  * //               MaxInstanceCount: Number("int"),
+ * //               ScaleInPolicy: {
+ * //                 Strategy: "IDLE_RELEASE" || "CONSOLIDATION", // required
+ * //                 MaximumStepSize: Number("int"),
+ * //                 CooldownInMinutes: Number("int"),
+ * //               },
  * //             },
  * //             RoutingConfig: {
  * //               RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required

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

@@ -61,6 +61,13 @@ declare const UpdateInferenceComponentCommand_base: {
  *     DataCacheConfig: { // InferenceComponentDataCacheConfig
  *       EnableCaching: true || false, // required
  *     },
+ *     SchedulingConfig: { // InferenceComponentSchedulingConfig
+ *       PlacementStrategy: "SPREAD" || "BINPACK", // required
+ *       AvailabilityZoneBalance: { // InferenceComponentAvailabilityZoneBalance
+ *         EnforcementMode: "PERMISSIVE", // required
+ *         MaxImbalance: Number("int"),
+ *       },
+ *     },
  *   },
  *   RuntimeConfig: { // InferenceComponentRuntimeConfig
  *     CopyCount: Number("int"), // required

package/dist-types/index.d.ts

@@ -5,7 +5,7 @@
  */
 export * from "./SageMakerClient";
 export * from "./SageMaker";
-export { ClientInputEndpointParameters } from "./endpoint/EndpointParameters";
+export type { ClientInputEndpointParameters } from "./endpoint/EndpointParameters";
 export type { RuntimeExtension } from "./runtimeExtensions";
 export type { SageMakerExtensionConfiguration } from "./extensionConfiguration";
 export * from "./commands";

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

@@ -1727,6 +1727,17 @@ export declare const AutotuneMode: {
  * @public
  */
 export type AutotuneMode = (typeof AutotuneMode)[keyof typeof AutotuneMode];
+/**
+ * @public
+ * @enum
+ */
+export declare const AvailabilityZoneBalanceEnforcementMode: {
+    readonly PERMISSIVE: "PERMISSIVE";
+};
+/**
+ * @public
+ */
+export type AvailabilityZoneBalanceEnforcementMode = (typeof AvailabilityZoneBalanceEnforcementMode)[keyof typeof AvailabilityZoneBalanceEnforcementMode];
 /**
  * @public
  * @enum
@@ -2998,6 +3009,18 @@ export declare const ProductionVariantInferenceAmiVersion: {
  * @public
  */
 export type ProductionVariantInferenceAmiVersion = (typeof ProductionVariantInferenceAmiVersion)[keyof typeof ProductionVariantInferenceAmiVersion];
+/**
+ * @public
+ * @enum
+ */
+export declare const ManagedInstanceScalingScaleInStrategy: {
+    readonly CONSOLIDATION: "CONSOLIDATION";
+    readonly IDLE_RELEASE: "IDLE_RELEASE";
+};
+/**
+ * @public
+ */
+export type ManagedInstanceScalingScaleInStrategy = (typeof ManagedInstanceScalingScaleInStrategy)[keyof typeof ManagedInstanceScalingScaleInStrategy];
 /**
  * @public
  * @enum
@@ -3190,6 +3213,18 @@ export declare const VendorGuidance: {
  * @public
  */
 export type VendorGuidance = (typeof VendorGuidance)[keyof typeof VendorGuidance];
+/**
+ * @public
+ * @enum
+ */
+export declare const InferenceComponentPlacementStrategy: {
+    readonly BINPACK: "BINPACK";
+    readonly SPREAD: "SPREAD";
+};
+/**
+ * @public
+ */
+export type InferenceComponentPlacementStrategy = (typeof InferenceComponentPlacementStrategy)[keyof typeof InferenceComponentPlacementStrategy];
 /**
  * @public
  * @enum

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

@@ -1,4 +1,4 @@
-import { ActionStatus, ActivationState, ActiveClusterOperationName, AdditionalS3DataSourceDataType, AggregationTransformationValue, AlgorithmStatus, AppInstanceType, AppStatus, AppType, ArtifactSourceIdType, AssemblyType, AssociationEdgeType, AsyncNotificationTopicTypes, AthenaResultCompressionType, AthenaResultFormat, AutoMLAlgorithm, AutoMLChannelType, AutoMLJobObjectiveType, AutoMLJobSecondaryStatus, AutoMLJobStatus, AutoMLMetricEnum, AutoMLMetricExtendedEnum, AutoMLMode, AutoMLProcessingUnit, AutoMLS3DataType, AutotuneMode, BatchAddClusterNodesErrorCode, BatchDeleteClusterNodesErrorCode, BatchRebootClusterNodesErrorCode, BatchReplaceClusterNodesErrorCode, BatchStrategy, CandidateStatus, CandidateStepType, CapacityReservationType, CapacitySizeType, CaptureMode, ClarifyFeatureType, ClarifyTextGranularity, ClarifyTextLanguage, ClusterAutoScalerType, ClusterAutoScalingMode, ClusterAutoScalingStatus, ClusterCapacityType, ClusterConfigMode, ClusterEventResourceType, ClusterInstanceStatus, ClusterInstanceType, ClusterKubernetesTaintEffect, ClusterNodeProvisioningMode, ClusterNodeRecovery, ClusterSlurmConfigStrategy, ClusterSlurmNodeType, ClusterStatus, CompilationJobStatus, CompleteOnConvergence, CompressionType, ConditionOutcome, ContainerMode, DataSourceName, DeepHealthCheckType, DetailedAlgorithmStatus, FairShare, FeatureStatus, FileSystemAccessMode, FileSystemType, FillingType, Framework, HyperParameterScalingType, HyperParameterTuningJobObjectiveType, IdleResourceSharing, InstanceGroupStatus, LifecycleManagement, MetricSetSource, MIGProfileType, ModelApprovalStatus, ModelCacheSetting, ModelCompressionType, ModelPackageRegistrationType, ModelPackageStatus, NodeUnavailabilityType, ObjectiveStatus, OutputCompressionType, ParameterType, PreemptTeamTasks, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, RecordWrapper, RepositoryAccessMode, ResourceSharingStrategy, S3DataDistribution, S3DataType, S3ModelDataType, SchedulerResourceStatus, SoftwareUpdateStatus, SplitType, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrafficRoutingConfigType, TrainingInputMode, TrainingInstanceType, TrainingRepositoryAccessMode, TransformInstanceType, VolumeAttachmentStatus } from "./enums";
+import type { ActionStatus, ActivationState, ActiveClusterOperationName, AdditionalS3DataSourceDataType, AggregationTransformationValue, AlgorithmStatus, AppInstanceType, AppStatus, AppType, ArtifactSourceIdType, AssemblyType, AssociationEdgeType, AsyncNotificationTopicTypes, AthenaResultCompressionType, AthenaResultFormat, AutoMLAlgorithm, AutoMLChannelType, AutoMLJobObjectiveType, AutoMLJobSecondaryStatus, AutoMLJobStatus, AutoMLMetricEnum, AutoMLMetricExtendedEnum, AutoMLMode, AutoMLProcessingUnit, AutoMLS3DataType, AutotuneMode, BatchAddClusterNodesErrorCode, BatchDeleteClusterNodesErrorCode, BatchRebootClusterNodesErrorCode, BatchReplaceClusterNodesErrorCode, BatchStrategy, CandidateStatus, CandidateStepType, CapacityReservationType, CapacitySizeType, CaptureMode, ClarifyFeatureType, ClarifyTextGranularity, ClarifyTextLanguage, ClusterAutoScalerType, ClusterAutoScalingMode, ClusterAutoScalingStatus, ClusterCapacityType, ClusterConfigMode, ClusterEventResourceType, ClusterInstanceStatus, ClusterInstanceType, ClusterKubernetesTaintEffect, ClusterNodeProvisioningMode, ClusterNodeRecovery, ClusterSlurmConfigStrategy, ClusterSlurmNodeType, ClusterStatus, CompilationJobStatus, CompleteOnConvergence, CompressionType, ConditionOutcome, ContainerMode, DataSourceName, DeepHealthCheckType, DetailedAlgorithmStatus, FairShare, FeatureStatus, FileSystemAccessMode, FileSystemType, FillingType, Framework, HyperParameterScalingType, HyperParameterTuningJobObjectiveType, IdleResourceSharing, InstanceGroupStatus, LifecycleManagement, MetricSetSource, MIGProfileType, ModelApprovalStatus, ModelCacheSetting, ModelCompressionType, ModelPackageRegistrationType, ModelPackageStatus, NodeUnavailabilityType, ObjectiveStatus, OutputCompressionType, ParameterType, PreemptTeamTasks, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, RecordWrapper, RepositoryAccessMode, ResourceSharingStrategy, S3DataDistribution, S3DataType, S3ModelDataType, SchedulerResourceStatus, SoftwareUpdateStatus, SplitType, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrafficRoutingConfigType, TrainingInputMode, TrainingInstanceType, TrainingRepositoryAccessMode, TransformInstanceType, VolumeAttachmentStatus } from "./enums";
 /**
  * <p>Configuration for allocating accelerator partitions.</p>
  * @public

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

@@ -1,6 +1,6 @@
 import { AutomaticJsonStringConversion as __AutomaticJsonStringConversion } from "@smithy/smithy-client";
-import { _InstanceType, AccountDefaultStatus, ActivationState, AppInstanceType, AppNetworkAccessType, AppSecurityGroupManagement, AppType, AuthMode, AutoMountHomeEFS, AwsManagedHumanLoopRequestSource, CapacityReservationPreference, CollectionType, ContentClassifier, DataDistributionType, DeviceSubsetType, DirectInternetAccess, EdgePresetDeploymentType, ExecutionRoleIdentityConfig, FailureHandlingPolicy, FeatureStatus, FeatureType, FlatInvocations, HubContentType, HyperParameterScalingType, HyperParameterTuningAllocationStrategy, HyperParameterTuningJobStrategyType, HyperParameterTuningJobWarmStartType, InferenceExecutionMode, InferenceExperimentType, InputMode, IPAddressType, JobType, ManagedInstanceScalingStatus, MetricPublishFrequencyInSeconds, MlTools, ModelApprovalStatus, ModelCardStatus, ModelInfrastructureType, ModelPackageRegistrationType, ModelRegistrationMode, ModelSpeculativeDecodingS3DataType, ModelSpeculativeDecodingTechnique, MonitoringProblemType, MonitoringType, NotebookInstanceAcceleratorType, NotebookOutputOption, OptimizationJobDeploymentInstanceType, PartnerAppAuthType, PartnerAppType, ProcessingInstanceType, ProcessingS3CompressionType, ProcessingS3DataDistributionType, ProcessingS3DataType, ProcessingS3InputMode, ProcessingS3UploadMode, Processor, ProductionVariantAcceleratorType, ProductionVariantInferenceAmiVersion, ProductionVariantInstanceType, RecommendationJobSupportedEndpointType, RecommendationJobType, RedshiftResultCompressionType, RedshiftResultFormat, RootAccess, RoutingStrategy, RStudioServerProAccessStatus, RStudioServerProUserGroup, SageMakerImageName, SkipModelValidation, StorageType, StudioWebPortal, TableFormat, TagPropagation, TargetDevice, ThroughputMode, TrackingServerSize, TrafficType, TrainingInputMode, TrainingInstanceType, TrainingJobEarlyStoppingType, TtlDurationUnit, VendorGuidance } from "./enums";
-import { type AmazonQSettings, type AnnotationConsolidationConfig, type AppLifecycleManagement, type AppSpecification, type AsyncInferenceConfig, type AthenaDatasetDefinition, type AutoRollbackConfig, type Autotune, type BatchTransformInput, type BestObjectiveNotImproving, type Bias, type BlueGreenUpdatePolicy, type CanvasAppSettings, type CapacitySize, type CaptureContentTypeHeader, type CfnCreateTemplateProvider, type CheckpointConfig, type ClarifyExplainerConfig, type CodeEditorAppSettings, type CollectionConfig, type ComputeQuotaConfig, type ComputeQuotaTarget, type ContextSource, type ConvergenceDetected, type HyperParameterTuningJobObjective, type InferenceSpecification, type InputConfig, type MetadataProperties, type MetricsSource, type ModelDataSource, type OutputDataConfig, type ResourceConfig, type ResourceSpec, type StoppingCondition, type TargetPlatform, type TransformJobDefinition, type VpcConfig, AdditionalInferenceSpecificationDefinition, AuthorizedUrl, AutoParameter, CaptureOption, CategoricalParameter, CategoricalParameterRange, Channel, CodeRepository, ContainerDefinition, ContinuousParameterRange, CustomImage, MetricDefinition, Tag } from "./models_0";
+import type { _InstanceType, AccountDefaultStatus, ActivationState, AppInstanceType, AppNetworkAccessType, AppSecurityGroupManagement, AppType, AuthMode, AutoMountHomeEFS, AvailabilityZoneBalanceEnforcementMode, AwsManagedHumanLoopRequestSource, CapacityReservationPreference, CollectionType, ContentClassifier, DataDistributionType, DeviceSubsetType, DirectInternetAccess, EdgePresetDeploymentType, ExecutionRoleIdentityConfig, FailureHandlingPolicy, FeatureStatus, FeatureType, FlatInvocations, HubContentType, HyperParameterScalingType, HyperParameterTuningAllocationStrategy, HyperParameterTuningJobStrategyType, HyperParameterTuningJobWarmStartType, InferenceComponentPlacementStrategy, InferenceExecutionMode, InferenceExperimentType, InputMode, IPAddressType, JobType, ManagedInstanceScalingScaleInStrategy, ManagedInstanceScalingStatus, MetricPublishFrequencyInSeconds, MlTools, ModelApprovalStatus, ModelCardStatus, ModelInfrastructureType, ModelPackageRegistrationType, ModelRegistrationMode, ModelSpeculativeDecodingS3DataType, ModelSpeculativeDecodingTechnique, MonitoringProblemType, MonitoringType, NotebookInstanceAcceleratorType, NotebookOutputOption, OptimizationJobDeploymentInstanceType, PartnerAppAuthType, PartnerAppType, ProcessingInstanceType, ProcessingS3CompressionType, ProcessingS3DataDistributionType, ProcessingS3DataType, ProcessingS3InputMode, ProcessingS3UploadMode, Processor, ProductionVariantAcceleratorType, ProductionVariantInferenceAmiVersion, ProductionVariantInstanceType, RecommendationJobSupportedEndpointType, RecommendationJobType, RedshiftResultCompressionType, RedshiftResultFormat, RootAccess, RoutingStrategy, RStudioServerProAccessStatus, RStudioServerProUserGroup, SageMakerImageName, SkipModelValidation, StorageType, StudioWebPortal, TableFormat, TagPropagation, TargetDevice, ThroughputMode, TrackingServerSize, TrafficType, TrainingInputMode, TrainingInstanceType, TrainingJobEarlyStoppingType, TtlDurationUnit, VendorGuidance } from "./enums";
+import type { AdditionalInferenceSpecificationDefinition, AmazonQSettings, AnnotationConsolidationConfig, AppLifecycleManagement, AppSpecification, AsyncInferenceConfig, AthenaDatasetDefinition, AuthorizedUrl, AutoParameter, AutoRollbackConfig, Autotune, BatchTransformInput, BestObjectiveNotImproving, Bias, BlueGreenUpdatePolicy, CanvasAppSettings, CapacitySize, CaptureContentTypeHeader, CaptureOption, CategoricalParameter, CategoricalParameterRange, CfnCreateTemplateProvider, Channel, CheckpointConfig, ClarifyExplainerConfig, CodeEditorAppSettings, CodeRepository, CollectionConfig, ComputeQuotaConfig, ComputeQuotaTarget, ContainerDefinition, ContextSource, ContinuousParameterRange, ConvergenceDetected, CustomImage, HyperParameterTuningJobObjective, InferenceSpecification, InputConfig, MetadataProperties, MetricDefinition, MetricsSource, ModelDataSource, OutputDataConfig, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TargetPlatform, TransformJobDefinition, VpcConfig } from "./models_0";
 /**
  * <p>Contains information about the output location for the compiled model and the target device that the model runs on. <code>TargetDevice</code> and <code>TargetPlatform</code> are mutually exclusive, so you need to choose one between the two to specify your target device or platform. If you cannot find your device you want to use from the <code>TargetDevice</code> list, use <code>TargetPlatform</code> to describe the platform of your edge device and <code>CompilerOptions</code> if there are specific settings that are required or recommended to use for particular TargetPlatform.</p>
  * @public
@@ -1692,6 +1692,27 @@ export interface ProductionVariantCoreDumpConfig {
      */
     KmsKeyId?: string | undefined;
 }
+/**
+ * <p>Configures the scale-in behavior for managed instance scaling.</p>
+ * @public
+ */
+export interface ProductionVariantManagedInstanceScalingScaleInPolicy {
+    /**
+     * <p>The strategy for scaling in instances.</p> <dl> <dt>IDLE_RELEASE</dt> <dd> <p>Releases instances that have no hosted inference component copies.</p> </dd> <dt>CONSOLIDATION</dt> <dd> <p>Consolidates inference component copies onto fewer instances to release more instances. Consolidation honors the scheduling configuration of each inference component. For example, if an inference component specifies Availability Zone balance, consolidation only proceeds when the resulting distribution does not increase the imbalance.</p> </dd> </dl>
+     * @public
+     */
+    Strategy: ManagedInstanceScalingScaleInStrategy | undefined;
+    /**
+     * <p>The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation.</p> <p>Default value: <code>1</code>.</p>
+     * @public
+     */
+    MaximumStepSize?: number | undefined;
+    /**
+     * <p>The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities.</p> <p>Default value: <code>20</code>.</p>
+     * @public
+     */
+    CooldownInMinutes?: number | undefined;
+}
 /**
  * <p>Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic. </p>
  * @public
@@ -1712,6 +1733,11 @@ export interface ProductionVariantManagedInstanceScaling {
      * @public
      */
     MaxInstanceCount?: number | undefined;
+    /**
+     * <p>Configures the scale-in behavior for managed instance scaling.</p>
+     * @public
+     */
+    ScaleInPolicy?: ProductionVariantManagedInstanceScalingScaleInPolicy | undefined;
 }
 /**
  * <p>Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.</p>
@@ -3182,6 +3208,38 @@ export interface InferenceComponentDataCacheConfig {
      */
     EnableCaching: boolean | undefined;
 }
+/**
+ * <p>Configuration for balancing inference component copies across Availability Zones.</p>
+ * @public
+ */
+export interface InferenceComponentAvailabilityZoneBalance {
+    /**
+     * <p>Determines how strictly the Availability Zone balance constraint is enforced.</p> <dl> <dt>PERMISSIVE</dt> <dd> <p>The endpoint attempts to balance copies across Availability Zones but proceeds with scheduling even if balance can't be achieved due to available capacity or instance distribution across Availability Zones.</p> </dd> </dl>
+     * @public
+     */
+    EnforcementMode: AvailabilityZoneBalanceEnforcementMode | undefined;
+    /**
+     * <p>The maximum allowed difference in the number of inference component copies between any two Availability Zones. This parameter applies only when the endpoint has instances across two or more Availability Zones. A copy placement is allowed if it reduces imbalance or the resulting imbalance is within this value.</p> <p>Default value: <code>0</code>.</p>
+     * @public
+     */
+    MaxImbalance?: number | undefined;
+}
+/**
+ * <p>The scheduling configuration that determines how inference component copies are placed across available instances when copies are added or removed.</p>
+ * @public
+ */
+export interface InferenceComponentSchedulingConfig {
+    /**
+     * <p>The strategy for placing inference component copies across available instances. If you also set <code>AvailabilityZoneBalance</code>, this strategy applies to placement within each Availability Zone.</p> <dl> <dt>SPREAD</dt> <dd> <p>Distributes copies evenly across available instances for better resilience.</p> </dd> <dt>BINPACK</dt> <dd> <p>Packs copies onto fewer instances to optimize resource utilization.</p> </dd> </dl>
+     * @public
+     */
+    PlacementStrategy: InferenceComponentPlacementStrategy | undefined;
+    /**
+     * <p>Configuration for balancing inference component copies across Availability Zones.</p>
+     * @public
+     */
+    AvailabilityZoneBalance?: InferenceComponentAvailabilityZoneBalance | undefined;
+}
 /**
  * <p>Settings that take effect while the model container starts up.</p>
  * @public
@@ -3233,6 +3291,11 @@ export interface InferenceComponentSpecification {
      * @public
      */
     DataCacheConfig?: InferenceComponentDataCacheConfig | undefined;
+    /**
+     * <p>The scheduling configuration that determines how inference component copies are placed across available instances when copies are added or removed.</p>
+     * @public
+     */
+    SchedulingConfig?: InferenceComponentSchedulingConfig | undefined;
 }
 /**
  * @public
@@ -6904,94 +6967,3 @@ export interface S3FileSystem {
      */
     S3Uri: string | undefined;
 }
-/**
- * <p>A file system, created by you, that you assign to a user profile or space for an Amazon SageMaker AI Domain. Permitted users can access this file system in Amazon SageMaker AI Studio.</p>
- * @public
- */
-export type CustomFileSystem = CustomFileSystem.EFSFileSystemMember | CustomFileSystem.FSxLustreFileSystemMember | CustomFileSystem.S3FileSystemMember | CustomFileSystem.$UnknownMember;
-/**
- * @public
- */
-export declare namespace CustomFileSystem {
-    /**
-     * <p>A custom file system in Amazon EFS.</p>
-     * @public
-     */
-    interface EFSFileSystemMember {
-        EFSFileSystem: EFSFileSystem;
-        FSxLustreFileSystem?: never;
-        S3FileSystem?: never;
-        $unknown?: never;
-    }
-    /**
-     * <p>A custom file system in Amazon FSx for Lustre.</p>
-     * @public
-     */
-    interface FSxLustreFileSystemMember {
-        EFSFileSystem?: never;
-        FSxLustreFileSystem: FSxLustreFileSystem;
-        S3FileSystem?: never;
-        $unknown?: never;
-    }
-    /**
-     * <p>A custom file system in Amazon S3. This is only supported in Amazon SageMaker Unified Studio.</p>
-     * @public
-     */
-    interface S3FileSystemMember {
-        EFSFileSystem?: never;
-        FSxLustreFileSystem?: never;
-        S3FileSystem: S3FileSystem;
-        $unknown?: never;
-    }
-    /**
-     * @public
-     */
-    interface $UnknownMember {
-        EFSFileSystem?: never;
-        FSxLustreFileSystem?: never;
-        S3FileSystem?: never;
-        $unknown: [string, any];
-    }
-    /**
-     * @deprecated unused in schema-serde mode.
-     *
-     */
-    interface Visitor<T> {
-        EFSFileSystem: (value: EFSFileSystem) => T;
-        FSxLustreFileSystem: (value: FSxLustreFileSystem) => T;
-        S3FileSystem: (value: S3FileSystem) => T;
-        _: (name: string, value: any) => T;
-    }
-}
-/**
- * <p>The settings for the JupyterLab application within a space.</p>
- * @public
- */
-export interface SpaceJupyterLabAppSettings {
-    /**
-     * <p>Specifies the ARN's of a SageMaker AI image and SageMaker AI image version, and the instance type that the version runs on.</p> <note> <p>When both <code>SageMakerImageVersionArn</code> and <code>SageMakerImageArn</code> are passed, <code>SageMakerImageVersionArn</code> is used. Any updates to <code>SageMakerImageArn</code> will not take effect if <code>SageMakerImageVersionArn</code> already exists in the <code>ResourceSpec</code> because <code>SageMakerImageVersionArn</code> always takes precedence. To clear the value set for <code>SageMakerImageVersionArn</code>, pass <code>None</code> as the value.</p> </note>
-     * @public
-     */
-    DefaultResourceSpec?: ResourceSpec | undefined;
-    /**
-     * <p>A list of Git repositories that SageMaker automatically displays to users for cloning in the JupyterLab application.</p>
-     * @public
-     */
-    CodeRepositories?: CodeRepository[] | undefined;
-    /**
-     * <p>Settings that are used to configure and manage the lifecycle of JupyterLab applications in a space.</p>
-     * @public
-     */
-    AppLifecycleManagement?: SpaceAppLifecycleManagement | undefined;
-}
-/**
- * <p>A collection of EBS storage settings that apply to both private and shared spaces.</p>
- * @public
- */
-export interface EbsStorageSettings {
-    /**
-     * <p>The size of an EBS storage volume for a space.</p>
-     * @public
-     */
-    EbsVolumeSizeInGb: number | undefined;
-}