@aws-sdk/client-sagemaker 3.844.0 → 3.846.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (69) hide show
  1. package/README.md +16 -0
  2. package/dist-cjs/index.js +223 -44
  3. package/dist-es/SageMaker.js +4 -0
  4. package/dist-es/commands/ListPipelineVersionsCommand.js +22 -0
  5. package/dist-es/commands/SearchCommand.js +1 -1
  6. package/dist-es/commands/UpdatePipelineVersionCommand.js +22 -0
  7. package/dist-es/commands/index.js +2 -0
  8. package/dist-es/models/models_0.js +0 -5
  9. package/dist-es/models/models_1.js +5 -4
  10. package/dist-es/models/models_2.js +4 -0
  11. package/dist-es/models/models_3.js +1 -10
  12. package/dist-es/models/models_4.js +10 -11
  13. package/dist-es/models/models_5.js +12 -0
  14. package/dist-es/pagination/ListPipelineVersionsPaginator.js +4 -0
  15. package/dist-es/pagination/index.js +1 -0
  16. package/dist-es/protocols/Aws_json1_1.js +140 -0
  17. package/dist-types/SageMaker.d.ts +14 -0
  18. package/dist-types/SageMakerClient.d.ts +4 -2
  19. package/dist-types/commands/BatchDeleteClusterNodesCommand.d.ts +1 -1
  20. package/dist-types/commands/CreateClusterCommand.d.ts +55 -0
  21. package/dist-types/commands/DescribeClusterCommand.d.ts +59 -0
  22. package/dist-types/commands/DescribeClusterNodeCommand.d.ts +1 -1
  23. package/dist-types/commands/DescribeEndpointConfigCommand.d.ts +1 -1
  24. package/dist-types/commands/DescribeExperimentCommand.d.ts +1 -1
  25. package/dist-types/commands/DescribePipelineCommand.d.ts +3 -0
  26. package/dist-types/commands/DescribePipelineExecutionCommand.d.ts +1 -0
  27. package/dist-types/commands/GetSearchSuggestionsCommand.d.ts +1 -1
  28. package/dist-types/commands/ListAppsCommand.d.ts +2 -1
  29. package/dist-types/commands/ListArtifactsCommand.d.ts +1 -1
  30. package/dist-types/commands/ListPipelineVersionsCommand.d.ts +90 -0
  31. package/dist-types/commands/SearchCommand.d.ts +17 -3
  32. package/dist-types/commands/SearchTrainingPlanOfferingsCommand.d.ts +1 -1
  33. package/dist-types/commands/SendPipelineExecutionStepFailureCommand.d.ts +1 -2
  34. package/dist-types/commands/StartPipelineExecutionCommand.d.ts +1 -0
  35. package/dist-types/commands/UpdateClusterCommand.d.ts +55 -0
  36. package/dist-types/commands/UpdatePipelineCommand.d.ts +1 -0
  37. package/dist-types/commands/UpdatePipelineVersionCommand.d.ts +82 -0
  38. package/dist-types/commands/index.d.ts +2 -0
  39. package/dist-types/models/models_0.d.ts +183 -130
  40. package/dist-types/models/models_1.d.ts +133 -87
  41. package/dist-types/models/models_2.d.ts +104 -164
  42. package/dist-types/models/models_3.d.ts +191 -120
  43. package/dist-types/models/models_4.d.ts +274 -394
  44. package/dist-types/models/models_5.d.ts +442 -4
  45. package/dist-types/pagination/ListPipelineVersionsPaginator.d.ts +7 -0
  46. package/dist-types/pagination/index.d.ts +1 -0
  47. package/dist-types/protocols/Aws_json1_1.d.ts +18 -0
  48. package/dist-types/ts3.4/SageMaker.d.ts +34 -0
  49. package/dist-types/ts3.4/SageMakerClient.d.ts +12 -0
  50. package/dist-types/ts3.4/commands/DescribeEndpointConfigCommand.d.ts +1 -1
  51. package/dist-types/ts3.4/commands/DescribeExperimentCommand.d.ts +1 -1
  52. package/dist-types/ts3.4/commands/ListAppsCommand.d.ts +2 -1
  53. package/dist-types/ts3.4/commands/ListArtifactsCommand.d.ts +1 -1
  54. package/dist-types/ts3.4/commands/ListPipelineVersionsCommand.d.ts +51 -0
  55. package/dist-types/ts3.4/commands/SearchCommand.d.ts +1 -2
  56. package/dist-types/ts3.4/commands/SearchTrainingPlanOfferingsCommand.d.ts +1 -1
  57. package/dist-types/ts3.4/commands/SendPipelineExecutionStepFailureCommand.d.ts +4 -2
  58. package/dist-types/ts3.4/commands/UpdatePipelineVersionCommand.d.ts +51 -0
  59. package/dist-types/ts3.4/commands/index.d.ts +2 -0
  60. package/dist-types/ts3.4/models/models_0.d.ts +41 -34
  61. package/dist-types/ts3.4/models/models_1.d.ts +40 -27
  62. package/dist-types/ts3.4/models/models_2.d.ts +36 -44
  63. package/dist-types/ts3.4/models/models_3.d.ts +48 -39
  64. package/dist-types/ts3.4/models/models_4.d.ts +74 -100
  65. package/dist-types/ts3.4/models/models_5.d.ts +131 -2
  66. package/dist-types/ts3.4/pagination/ListPipelineVersionsPaginator.d.ts +11 -0
  67. package/dist-types/ts3.4/pagination/index.d.ts +1 -0
  68. package/dist-types/ts3.4/protocols/Aws_json1_1.d.ts +24 -0
  69. package/package.json +11 -11
@@ -2606,7 +2606,7 @@ export interface IamIdentity {
2606
2606
  SourceIdentity?: string | undefined;
2607
2607
  }
2608
2608
  /**
2609
- * <p>Information about the user who created or modified an experiment, trial, trial component, lineage group, project, or model card.</p>
2609
+ * <p>Information about the user who created or modified a SageMaker resource.</p>
2610
2610
  * @public
2611
2611
  */
2612
2612
  export interface UserContext {
@@ -2677,7 +2677,7 @@ export interface AssociationSummary {
2677
2677
  */
2678
2678
  CreationTime?: Date | undefined;
2679
2679
  /**
2680
- * <p>Information about the user who created or modified an experiment, trial, trial component, lineage group, project, or model card.</p>
2680
+ * <p>Information about the user who created or modified a SageMaker resource.</p>
2681
2681
  * @public
2682
2682
  */
2683
2683
  CreatedBy?: UserContext | undefined;
@@ -4242,7 +4242,7 @@ export interface BatchDeleteClusterNodesRequest {
4242
4242
  * <p>A list of node IDs to be deleted from the specified cluster.</p> <note> <ul> <li> <p>For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes.</p> </li> <li> <p>If you need to delete more than 99 instances, contact <a href="http://aws.amazon.com/contact-us/">Support</a> for assistance.</p> </li> </ul> </note>
4243
4243
  * @public
4244
4244
  */
4245
- NodeIds: string[] | undefined;
4245
+ NodeIds?: string[] | undefined;
4246
4246
  }
4247
4247
  /**
4248
4248
  * @public
@@ -6185,6 +6185,186 @@ export interface ClusterOrchestrator {
6185
6185
  */
6186
6186
  Eks: ClusterOrchestratorEksConfig | undefined;
6187
6187
  }
6188
+ /**
6189
+ * <p>Configuration settings for an Amazon FSx for Lustre file system to be used with the cluster.</p>
6190
+ * @public
6191
+ */
6192
+ export interface FSxLustreConfig {
6193
+ /**
6194
+ * <p>The storage capacity of the Amazon FSx for Lustre file system, specified in gibibytes (GiB).</p>
6195
+ * @public
6196
+ */
6197
+ SizeInGiB: number | undefined;
6198
+ /**
6199
+ * <p>The throughput capacity of the Amazon FSx for Lustre file system, measured in MB/s per TiB of storage.</p>
6200
+ * @public
6201
+ */
6202
+ PerUnitStorageThroughput: number | undefined;
6203
+ }
6204
+ /**
6205
+ * <p>The configuration details for the restricted instance groups (RIG) environment.</p>
6206
+ * @public
6207
+ */
6208
+ export interface EnvironmentConfigDetails {
6209
+ /**
6210
+ * <p>Configuration settings for an Amazon FSx for Lustre file system to be used with the cluster.</p>
6211
+ * @public
6212
+ */
6213
+ FSxLustreConfig?: FSxLustreConfig | undefined;
6214
+ /**
6215
+ * <p>The Amazon S3 path where output data from the restricted instance group (RIG) environment will be stored.</p>
6216
+ * @public
6217
+ */
6218
+ S3OutputPath?: string | undefined;
6219
+ }
6220
+ /**
6221
+ * <p>The instance group details of the restricted instance group (RIG).</p>
6222
+ * @public
6223
+ */
6224
+ export interface ClusterRestrictedInstanceGroupDetails {
6225
+ /**
6226
+ * <p>The number of instances that are currently in the restricted instance group of a SageMaker HyperPod cluster.</p>
6227
+ * @public
6228
+ */
6229
+ CurrentCount?: number | undefined;
6230
+ /**
6231
+ * <p>The number of instances you specified to add to the restricted instance group of a SageMaker HyperPod cluster.</p>
6232
+ * @public
6233
+ */
6234
+ TargetCount?: number | undefined;
6235
+ /**
6236
+ * <p>The name of the restricted instance group of a SageMaker HyperPod cluster.</p>
6237
+ * @public
6238
+ */
6239
+ InstanceGroupName?: string | undefined;
6240
+ /**
6241
+ * <p>The instance type of the restricted instance group of a SageMaker HyperPod cluster.</p>
6242
+ * @public
6243
+ */
6244
+ InstanceType?: ClusterInstanceType | undefined;
6245
+ /**
6246
+ * <p>The execution role for the restricted instance group to assume.</p>
6247
+ * @public
6248
+ */
6249
+ ExecutionRole?: string | undefined;
6250
+ /**
6251
+ * <p>The number you specified to <code>TreadsPerCore</code> in <code>CreateCluster</code> for enabling or disabling multithreading. For instance types that support multithreading, you can specify 1 for disabling multithreading and 2 for enabling multithreading. For more information, see the reference table of <a href="https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/cpu-options-supported-instances-values.html">CPU cores and threads per CPU core per instance type</a> in the <i>Amazon Elastic Compute Cloud User Guide</i>.</p>
6252
+ * @public
6253
+ */
6254
+ ThreadsPerCore?: number | undefined;
6255
+ /**
6256
+ * <p>The additional storage configurations for the instances in the SageMaker HyperPod cluster restricted instance group.</p>
6257
+ * @public
6258
+ */
6259
+ InstanceStorageConfigs?: ClusterInstanceStorageConfig[] | undefined;
6260
+ /**
6261
+ * <p>A flag indicating whether deep health checks should be performed when the cluster's restricted instance group is created or updated.</p>
6262
+ * @public
6263
+ */
6264
+ OnStartDeepHealthChecks?: DeepHealthCheckType[] | undefined;
6265
+ /**
6266
+ * <p>The current status of the cluster's restricted instance group.</p> <ul> <li> <p> <code>InService</code>: The restricted instance group is active and healthy.</p> </li> <li> <p> <code>Creating</code>: The restricted instance group is being provisioned.</p> </li> <li> <p> <code>Updating</code>: The restricted instance group is being updated.</p> </li> <li> <p> <code>Failed</code>: The restricted instance group has failed to provision or is no longer healthy.</p> </li> <li> <p> <code>Degraded</code>: The restricted instance group is degraded, meaning that some instances have failed to provision or are no longer healthy.</p> </li> <li> <p> <code>Deleting</code>: The restricted instance group is being deleted.</p> </li> </ul>
6267
+ * @public
6268
+ */
6269
+ Status?: InstanceGroupStatus | undefined;
6270
+ /**
6271
+ * <p>The Amazon Resource Name (ARN) of the training plan to filter clusters by. For more information about reserving GPU capacity for your SageMaker HyperPod clusters using Amazon SageMaker Training Plan, see <code> <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateTrainingPlan.html">CreateTrainingPlan</a> </code>.</p>
6272
+ * @public
6273
+ */
6274
+ TrainingPlanArn?: string | undefined;
6275
+ /**
6276
+ * <p>The current status of the training plan associated with this cluster restricted instance group.</p>
6277
+ * @public
6278
+ */
6279
+ TrainingPlanStatus?: string | undefined;
6280
+ /**
6281
+ * <p>Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html">Give SageMaker Access to Resources in your Amazon VPC</a>. </p>
6282
+ * @public
6283
+ */
6284
+ OverrideVpcConfig?: VpcConfig | undefined;
6285
+ /**
6286
+ * <p>The configuration object of the schedule that SageMaker follows when updating the AMI.</p>
6287
+ * @public
6288
+ */
6289
+ ScheduledUpdateConfig?: ScheduledUpdateConfig | undefined;
6290
+ /**
6291
+ * <p>The configuration for the restricted instance groups (RIG) environment.</p>
6292
+ * @public
6293
+ */
6294
+ EnvironmentConfig?: EnvironmentConfigDetails | undefined;
6295
+ }
6296
+ /**
6297
+ * <p>The configuration for the restricted instance groups (RIG) environment.</p>
6298
+ * @public
6299
+ */
6300
+ export interface EnvironmentConfig {
6301
+ /**
6302
+ * <p>Configuration settings for an Amazon FSx for Lustre file system to be used with the cluster.</p>
6303
+ * @public
6304
+ */
6305
+ FSxLustreConfig?: FSxLustreConfig | undefined;
6306
+ }
6307
+ /**
6308
+ * <p>The specifications of a restricted instance group that you need to define.</p>
6309
+ * @public
6310
+ */
6311
+ export interface ClusterRestrictedInstanceGroupSpecification {
6312
+ /**
6313
+ * <p>Specifies the number of instances to add to the restricted instance group of a SageMaker HyperPod cluster.</p>
6314
+ * @public
6315
+ */
6316
+ InstanceCount: number | undefined;
6317
+ /**
6318
+ * <p>Specifies the name of the restricted instance group.</p>
6319
+ * @public
6320
+ */
6321
+ InstanceGroupName: string | undefined;
6322
+ /**
6323
+ * <p>Specifies the instance type of the restricted instance group.</p>
6324
+ * @public
6325
+ */
6326
+ InstanceType: ClusterInstanceType | undefined;
6327
+ /**
6328
+ * <p>Specifies an IAM execution role to be assumed by the restricted instance group.</p>
6329
+ * @public
6330
+ */
6331
+ ExecutionRole: string | undefined;
6332
+ /**
6333
+ * <p>The number you specified to <code>TreadsPerCore</code> in <code>CreateCluster</code> for enabling or disabling multithreading. For instance types that support multithreading, you can specify 1 for disabling multithreading and 2 for enabling multithreading. For more information, see the reference table of <a href="https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/cpu-options-supported-instances-values.html">CPU cores and threads per CPU core per instance type</a> in the <i>Amazon Elastic Compute Cloud User Guide</i>.</p>
6334
+ * @public
6335
+ */
6336
+ ThreadsPerCore?: number | undefined;
6337
+ /**
6338
+ * <p>Specifies the additional storage configurations for the instances in the SageMaker HyperPod cluster restricted instance group.</p>
6339
+ * @public
6340
+ */
6341
+ InstanceStorageConfigs?: ClusterInstanceStorageConfig[] | undefined;
6342
+ /**
6343
+ * <p>A flag indicating whether deep health checks should be performed when the cluster restricted instance group is created or updated.</p>
6344
+ * @public
6345
+ */
6346
+ OnStartDeepHealthChecks?: DeepHealthCheckType[] | undefined;
6347
+ /**
6348
+ * <p>The Amazon Resource Name (ARN) of the training plan to filter clusters by. For more information about reserving GPU capacity for your SageMaker HyperPod clusters using Amazon SageMaker Training Plan, see <code> <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateTrainingPlan.html">CreateTrainingPlan</a> </code>.</p>
6349
+ * @public
6350
+ */
6351
+ TrainingPlanArn?: string | undefined;
6352
+ /**
6353
+ * <p>Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html">Give SageMaker Access to Resources in your Amazon VPC</a>. </p>
6354
+ * @public
6355
+ */
6356
+ OverrideVpcConfig?: VpcConfig | undefined;
6357
+ /**
6358
+ * <p>The configuration object of the schedule that SageMaker follows when updating the AMI.</p>
6359
+ * @public
6360
+ */
6361
+ ScheduledUpdateConfig?: ScheduledUpdateConfig | undefined;
6362
+ /**
6363
+ * <p>The configuration for the restricted instance groups (RIG) environment.</p>
6364
+ * @public
6365
+ */
6366
+ EnvironmentConfig: EnvironmentConfig | undefined;
6367
+ }
6188
6368
  /**
6189
6369
  * @public
6190
6370
  * @enum
@@ -6765,130 +6945,3 @@ export declare const PreemptTeamTasks: {
6765
6945
  * @public
6766
6946
  */
6767
6947
  export type PreemptTeamTasks = (typeof PreemptTeamTasks)[keyof typeof PreemptTeamTasks];
6768
- /**
6769
- * @public
6770
- * @enum
6771
- */
6772
- export declare const ResourceSharingStrategy: {
6773
- readonly DONTLEND: "DontLend";
6774
- readonly LEND: "Lend";
6775
- readonly LENDANDBORROW: "LendAndBorrow";
6776
- };
6777
- /**
6778
- * @public
6779
- */
6780
- export type ResourceSharingStrategy = (typeof ResourceSharingStrategy)[keyof typeof ResourceSharingStrategy];
6781
- /**
6782
- * <p>Resource sharing configuration.</p>
6783
- * @public
6784
- */
6785
- export interface ResourceSharingConfig {
6786
- /**
6787
- * <p>The strategy of how idle compute is shared within the cluster. The following are the options of strategies.</p> <ul> <li> <p> <code>DontLend</code>: entities do not lend idle compute.</p> </li> <li> <p> <code>Lend</code>: entities can lend idle compute to entities that can borrow.</p> </li> <li> <p> <code>LendandBorrow</code>: entities can lend idle compute and borrow idle compute from other entities.</p> </li> </ul> <p>Default is <code>LendandBorrow</code>.</p>
6788
- * @public
6789
- */
6790
- Strategy: ResourceSharingStrategy | undefined;
6791
- /**
6792
- * <p>The limit on how much idle compute can be borrowed.The values can be 1 - 500 percent of idle compute that the team is allowed to borrow.</p> <p>Default is <code>50</code>.</p>
6793
- * @public
6794
- */
6795
- BorrowLimit?: number | undefined;
6796
- }
6797
- /**
6798
- * <p>Configuration of the compute allocation definition for an entity. This includes the resource sharing option and the setting to preempt low priority tasks.</p>
6799
- * @public
6800
- */
6801
- export interface ComputeQuotaConfig {
6802
- /**
6803
- * <p>Allocate compute resources by instance types.</p>
6804
- * @public
6805
- */
6806
- ComputeQuotaResources?: ComputeQuotaResourceConfig[] | undefined;
6807
- /**
6808
- * <p>Resource sharing configuration. This defines how an entity can lend and borrow idle compute with other entities within the cluster.</p>
6809
- * @public
6810
- */
6811
- ResourceSharingConfig?: ResourceSharingConfig | undefined;
6812
- /**
6813
- * <p>Allows workloads from within an entity to preempt same-team workloads. When set to <code>LowerPriority</code>, the entity's lower priority tasks are preempted by their own higher priority tasks.</p> <p>Default is <code>LowerPriority</code>.</p>
6814
- * @public
6815
- */
6816
- PreemptTeamTasks?: PreemptTeamTasks | undefined;
6817
- }
6818
- /**
6819
- * <p>The target entity to allocate compute resources to.</p>
6820
- * @public
6821
- */
6822
- export interface ComputeQuotaTarget {
6823
- /**
6824
- * <p>Name of the team to allocate compute resources to.</p>
6825
- * @public
6826
- */
6827
- TeamName: string | undefined;
6828
- /**
6829
- * <p>Assigned entity fair-share weight. Idle compute will be shared across entities based on these assigned weights. This weight is only used when <code>FairShare</code> is enabled.</p> <p>A weight of 0 is the lowest priority and 100 is the highest. Weight 0 is the default.</p>
6830
- * @public
6831
- */
6832
- FairShareWeight?: number | undefined;
6833
- }
6834
- /**
6835
- * <p>Summary of the compute allocation definition.</p>
6836
- * @public
6837
- */
6838
- export interface ComputeQuotaSummary {
6839
- /**
6840
- * <p>ARN of the compute allocation definition.</p>
6841
- * @public
6842
- */
6843
- ComputeQuotaArn: string | undefined;
6844
- /**
6845
- * <p>ID of the compute allocation definition.</p>
6846
- * @public
6847
- */
6848
- ComputeQuotaId: string | undefined;
6849
- /**
6850
- * <p>Name of the compute allocation definition.</p>
6851
- * @public
6852
- */
6853
- Name: string | undefined;
6854
- /**
6855
- * <p>Version of the compute allocation definition.</p>
6856
- * @public
6857
- */
6858
- ComputeQuotaVersion?: number | undefined;
6859
- /**
6860
- * <p>Status of the compute allocation definition.</p>
6861
- * @public
6862
- */
6863
- Status: SchedulerResourceStatus | undefined;
6864
- /**
6865
- * <p>ARN of the cluster.</p>
6866
- * @public
6867
- */
6868
- ClusterArn?: string | undefined;
6869
- /**
6870
- * <p>Configuration of the compute allocation definition. This includes the resource sharing option, and the setting to preempt low priority tasks.</p>
6871
- * @public
6872
- */
6873
- ComputeQuotaConfig?: ComputeQuotaConfig | undefined;
6874
- /**
6875
- * <p>The target entity to allocate compute resources to.</p>
6876
- * @public
6877
- */
6878
- ComputeQuotaTarget: ComputeQuotaTarget | undefined;
6879
- /**
6880
- * <p>The state of the compute allocation being described. Use to enable or disable compute allocation.</p> <p>Default is <code>Enabled</code>.</p>
6881
- * @public
6882
- */
6883
- ActivationState?: ActivationState | undefined;
6884
- /**
6885
- * <p>Creation time of the compute allocation definition.</p>
6886
- * @public
6887
- */
6888
- CreationTime: Date | undefined;
6889
- /**
6890
- * <p>Last modified time of the compute allocation definition.</p>
6891
- * @public
6892
- */
6893
- LastModifiedTime?: Date | undefined;
6894
- }
@@ -1,6 +1,133 @@
1
1
  import { AutomaticJsonStringConversion as __AutomaticJsonStringConversion, ExceptionOptionType as __ExceptionOptionType } from "@smithy/smithy-client";
2
- import { ActionSource, ActionStatus, ActivationState, AdditionalModelDataSource, AdditionalS3DataSource, AlgorithmValidationSpecification, AmazonQSettings, AnnotationConsolidationConfig, AppInstanceType, AppLifecycleManagement, AppNetworkAccessType, AppSecurityGroupManagement, AppType, ArtifactSource, AsyncInferenceConfig, AuthMode, AuthorizedUrl, AutoMLChannel, AutoMLComputeConfig, AutoMLDataSplitConfig, AutoMLJobChannel, AutoMLJobConfig, AutoMLJobObjective, AutoMLOutputDataConfig, AutoMLProblemTypeConfig, AutoMLSecurityConfig, AutoMountHomeEFS, AutoParameter, AutoRollbackConfig, Autotune, AwsManagedHumanLoopRequestSource, BatchTransformInput, BestObjectiveNotImproving, Bias, BlueGreenUpdatePolicy, CanvasAppSettings, CapacityReservationPreference, CapacitySize, CaptureContentTypeHeader, CaptureOption, CategoricalParameter, CategoricalParameterRange, CategoricalParameterRangeSpecification, Channel, ChannelSpecification, CheckpointConfig, ClarifyExplainerConfig, ClusterInstanceGroupSpecification, ClusterNodeRecovery, ClusterOrchestrator, CodeEditorAppImageConfig, CodeEditorAppSettings, CodeRepository, CollectionConfig, CollectionType, CompleteOnConvergence, ComputeQuotaConfig, ComputeQuotaTarget, CustomImage, FeatureStatus, GitConfig, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, MetricDefinition, MetricsSource, ModelDataSource, OutputDataConfig, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, ResourceConfig, ResourceSpec, StoppingCondition, Tag, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrainingInputMode, TrainingInstanceType, VpcConfig } from "./models_0";
2
+ import { ActionSource, ActionStatus, ActivationState, AdditionalModelDataSource, AdditionalS3DataSource, AlgorithmValidationSpecification, AmazonQSettings, AnnotationConsolidationConfig, AppInstanceType, AppLifecycleManagement, AppNetworkAccessType, AppSecurityGroupManagement, AppType, ArtifactSource, AsyncInferenceConfig, AuthMode, AuthorizedUrl, AutoMLChannel, AutoMLComputeConfig, AutoMLDataSplitConfig, AutoMLJobChannel, AutoMLJobConfig, AutoMLJobObjective, AutoMLOutputDataConfig, AutoMLProblemTypeConfig, AutoMLSecurityConfig, AutoMountHomeEFS, AutoParameter, AutoRollbackConfig, Autotune, AwsManagedHumanLoopRequestSource, BatchTransformInput, BestObjectiveNotImproving, BlueGreenUpdatePolicy, CanvasAppSettings, CapacityReservationPreference, CapacitySize, CaptureContentTypeHeader, CaptureOption, CategoricalParameter, CategoricalParameterRange, CategoricalParameterRangeSpecification, Channel, ChannelSpecification, CheckpointConfig, ClarifyExplainerConfig, ClusterInstanceGroupSpecification, ClusterNodeRecovery, ClusterOrchestrator, ClusterRestrictedInstanceGroupSpecification, CodeEditorAppImageConfig, CodeEditorAppSettings, CodeRepository, CollectionConfig, CollectionType, CompleteOnConvergence, ComputeQuotaResourceConfig, CustomImage, FeatureStatus, GitConfig, InferenceSpecification, JupyterLabAppImageConfig, KernelGatewayImageConfig, MetricDefinition, MetricsSource, ModelDataSource, OutputDataConfig, PreemptTeamTasks, ProblemType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProductionVariantInstanceType, ResourceConfig, ResourceSpec, SchedulerResourceStatus, StoppingCondition, Tag, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrainingInputMode, TrainingInstanceType, VpcConfig } from "./models_0";
3
3
  import { SageMakerServiceException as __BaseException } from "./SageMakerServiceException";
4
+ /**
5
+ * @public
6
+ * @enum
7
+ */
8
+ export declare const ResourceSharingStrategy: {
9
+ readonly DONTLEND: "DontLend";
10
+ readonly LEND: "Lend";
11
+ readonly LENDANDBORROW: "LendAndBorrow";
12
+ };
13
+ /**
14
+ * @public
15
+ */
16
+ export type ResourceSharingStrategy = (typeof ResourceSharingStrategy)[keyof typeof ResourceSharingStrategy];
17
+ /**
18
+ * <p>Resource sharing configuration.</p>
19
+ * @public
20
+ */
21
+ export interface ResourceSharingConfig {
22
+ /**
23
+ * <p>The strategy of how idle compute is shared within the cluster. The following are the options of strategies.</p> <ul> <li> <p> <code>DontLend</code>: entities do not lend idle compute.</p> </li> <li> <p> <code>Lend</code>: entities can lend idle compute to entities that can borrow.</p> </li> <li> <p> <code>LendandBorrow</code>: entities can lend idle compute and borrow idle compute from other entities.</p> </li> </ul> <p>Default is <code>LendandBorrow</code>.</p>
24
+ * @public
25
+ */
26
+ Strategy: ResourceSharingStrategy | undefined;
27
+ /**
28
+ * <p>The limit on how much idle compute can be borrowed.The values can be 1 - 500 percent of idle compute that the team is allowed to borrow.</p> <p>Default is <code>50</code>.</p>
29
+ * @public
30
+ */
31
+ BorrowLimit?: number | undefined;
32
+ }
33
+ /**
34
+ * <p>Configuration of the compute allocation definition for an entity. This includes the resource sharing option and the setting to preempt low priority tasks.</p>
35
+ * @public
36
+ */
37
+ export interface ComputeQuotaConfig {
38
+ /**
39
+ * <p>Allocate compute resources by instance types.</p>
40
+ * @public
41
+ */
42
+ ComputeQuotaResources?: ComputeQuotaResourceConfig[] | undefined;
43
+ /**
44
+ * <p>Resource sharing configuration. This defines how an entity can lend and borrow idle compute with other entities within the cluster.</p>
45
+ * @public
46
+ */
47
+ ResourceSharingConfig?: ResourceSharingConfig | undefined;
48
+ /**
49
+ * <p>Allows workloads from within an entity to preempt same-team workloads. When set to <code>LowerPriority</code>, the entity's lower priority tasks are preempted by their own higher priority tasks.</p> <p>Default is <code>LowerPriority</code>.</p>
50
+ * @public
51
+ */
52
+ PreemptTeamTasks?: PreemptTeamTasks | undefined;
53
+ }
54
+ /**
55
+ * <p>The target entity to allocate compute resources to.</p>
56
+ * @public
57
+ */
58
+ export interface ComputeQuotaTarget {
59
+ /**
60
+ * <p>Name of the team to allocate compute resources to.</p>
61
+ * @public
62
+ */
63
+ TeamName: string | undefined;
64
+ /**
65
+ * <p>Assigned entity fair-share weight. Idle compute will be shared across entities based on these assigned weights. This weight is only used when <code>FairShare</code> is enabled.</p> <p>A weight of 0 is the lowest priority and 100 is the highest. Weight 0 is the default.</p>
66
+ * @public
67
+ */
68
+ FairShareWeight?: number | undefined;
69
+ }
70
+ /**
71
+ * <p>Summary of the compute allocation definition.</p>
72
+ * @public
73
+ */
74
+ export interface ComputeQuotaSummary {
75
+ /**
76
+ * <p>ARN of the compute allocation definition.</p>
77
+ * @public
78
+ */
79
+ ComputeQuotaArn: string | undefined;
80
+ /**
81
+ * <p>ID of the compute allocation definition.</p>
82
+ * @public
83
+ */
84
+ ComputeQuotaId: string | undefined;
85
+ /**
86
+ * <p>Name of the compute allocation definition.</p>
87
+ * @public
88
+ */
89
+ Name: string | undefined;
90
+ /**
91
+ * <p>Version of the compute allocation definition.</p>
92
+ * @public
93
+ */
94
+ ComputeQuotaVersion?: number | undefined;
95
+ /**
96
+ * <p>Status of the compute allocation definition.</p>
97
+ * @public
98
+ */
99
+ Status: SchedulerResourceStatus | undefined;
100
+ /**
101
+ * <p>ARN of the cluster.</p>
102
+ * @public
103
+ */
104
+ ClusterArn?: string | undefined;
105
+ /**
106
+ * <p>Configuration of the compute allocation definition. This includes the resource sharing option, and the setting to preempt low priority tasks.</p>
107
+ * @public
108
+ */
109
+ ComputeQuotaConfig?: ComputeQuotaConfig | undefined;
110
+ /**
111
+ * <p>The target entity to allocate compute resources to.</p>
112
+ * @public
113
+ */
114
+ ComputeQuotaTarget: ComputeQuotaTarget | undefined;
115
+ /**
116
+ * <p>The state of the compute allocation being described. Use to enable or disable compute allocation.</p> <p>Default is <code>Enabled</code>.</p>
117
+ * @public
118
+ */
119
+ ActivationState?: ActivationState | undefined;
120
+ /**
121
+ * <p>Creation time of the compute allocation definition.</p>
122
+ * @public
123
+ */
124
+ CreationTime: Date | undefined;
125
+ /**
126
+ * <p>Last modified time of the compute allocation definition.</p>
127
+ * @public
128
+ */
129
+ LastModifiedTime?: Date | undefined;
130
+ }
4
131
  /**
5
132
  * @public
6
133
  * @enum
@@ -928,6 +1055,11 @@ export interface CreateClusterRequest {
928
1055
  * @public
929
1056
  */
930
1057
  InstanceGroups?: ClusterInstanceGroupSpecification[] | undefined;
1058
+ /**
1059
+ * <p>The specialized instance groups for training models like Amazon Nova to be created in the SageMaker HyperPod cluster.</p>
1060
+ * @public
1061
+ */
1062
+ RestrictedInstanceGroups?: ClusterRestrictedInstanceGroupSpecification[] | undefined;
931
1063
  /**
932
1064
  * <p>Specifies the Amazon Virtual Private Cloud (VPC) that is associated with the Amazon SageMaker HyperPod cluster. You can control access to and from your resources by configuring your VPC. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html">Give SageMaker access to resources in your Amazon VPC</a>.</p> <note> <p>When your Amazon VPC and subnets support IPv6, network communications differ based on the cluster orchestration platform:</p> <ul> <li> <p>Slurm-orchestrated clusters automatically configure nodes with dual IPv6 and IPv4 addresses, allowing immediate IPv6 network communications.</p> </li> <li> <p>In Amazon EKS-orchestrated clusters, nodes receive dual-stack addressing, but pods can only use IPv6 when the Amazon EKS cluster is explicitly IPv6-enabled. For information about deploying an IPv6 Amazon EKS cluster, see <a href="https://docs.aws.amazon.com/eks/latest/userguide/deploy-ipv6-cluster.html#_deploy_an_ipv6_cluster_with_eksctl">Amazon EKS IPv6 Cluster Deployment</a>.</p> </li> </ul> <p>Additional resources for IPv6 configuration:</p> <ul> <li> <p>For information about adding IPv6 support to your VPC, see to <a href="https://docs.aws.amazon.com/vpc/latest/userguide/vpc-migrate-ipv6.html">IPv6 Support for VPC</a>.</p> </li> <li> <p>For information about creating a new IPv6-compatible VPC, see <a href="https://docs.aws.amazon.com/vpc/latest/userguide/create-vpc.html">Amazon VPC Creation Guide</a>.</p> </li> <li> <p>To configure SageMaker HyperPod with a custom Amazon VPC, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-prerequisites.html#sagemaker-hyperpod-prerequisites-optional-vpc">Custom Amazon VPC Setup for SageMaker HyperPod</a>.</p> </li> </ul> </note>
933
1065
  * @public
@@ -6662,92 +6794,6 @@ export interface ModelQuality {
6662
6794
  */
6663
6795
  Constraints?: MetricsSource | undefined;
6664
6796
  }
6665
- /**
6666
- * <p>Contains metrics captured from a model.</p>
6667
- * @public
6668
- */
6669
- export interface ModelMetrics {
6670
- /**
6671
- * <p>Metrics that measure the quality of a model.</p>
6672
- * @public
6673
- */
6674
- ModelQuality?: ModelQuality | undefined;
6675
- /**
6676
- * <p>Metrics that measure the quality of the input data for a model.</p>
6677
- * @public
6678
- */
6679
- ModelDataQuality?: ModelDataQuality | undefined;
6680
- /**
6681
- * <p>Metrics that measure bias in a model.</p>
6682
- * @public
6683
- */
6684
- Bias?: Bias | undefined;
6685
- /**
6686
- * <p>Metrics that help explain a model.</p>
6687
- * @public
6688
- */
6689
- Explainability?: Explainability | undefined;
6690
- }
6691
- /**
6692
- * <p>An optional Key Management Service key to encrypt, decrypt, and re-encrypt model package information for regulated workloads with highly sensitive data.</p>
6693
- * @public
6694
- */
6695
- export interface ModelPackageSecurityConfig {
6696
- /**
6697
- * <p>The KMS Key ID (<code>KMSKeyId</code>) used for encryption of model package information.</p>
6698
- * @public
6699
- */
6700
- KmsKeyId: string | undefined;
6701
- }
6702
- /**
6703
- * @public
6704
- * @enum
6705
- */
6706
- export declare const SkipModelValidation: {
6707
- readonly ALL: "All";
6708
- readonly NONE: "None";
6709
- };
6710
- /**
6711
- * @public
6712
- */
6713
- export type SkipModelValidation = (typeof SkipModelValidation)[keyof typeof SkipModelValidation];
6714
- /**
6715
- * <p>Specifies an algorithm that was used to create the model package. The algorithm must be either an algorithm resource in your SageMaker account or an algorithm in Amazon Web Services Marketplace that you are subscribed to.</p>
6716
- * @public
6717
- */
6718
- export interface SourceAlgorithm {
6719
- /**
6720
- * <p>The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single <code>gzip</code> compressed tar archive (<code>.tar.gz</code> suffix).</p> <note> <p>The model artifacts must be in an S3 bucket that is in the same Amazon Web Services region as the algorithm.</p> </note>
6721
- * @public
6722
- */
6723
- ModelDataUrl?: string | undefined;
6724
- /**
6725
- * <p>Specifies the location of ML model data to deploy during endpoint creation.</p>
6726
- * @public
6727
- */
6728
- ModelDataSource?: ModelDataSource | undefined;
6729
- /**
6730
- * <p>The ETag associated with Model Data URL.</p>
6731
- * @public
6732
- */
6733
- ModelDataETag?: string | undefined;
6734
- /**
6735
- * <p>The name of an algorithm that was used to create the model package. The algorithm must be either an algorithm resource in your SageMaker account or an algorithm in Amazon Web Services Marketplace that you are subscribed to.</p>
6736
- * @public
6737
- */
6738
- AlgorithmName: string | undefined;
6739
- }
6740
- /**
6741
- * <p>A list of algorithms that were used to create a model package.</p>
6742
- * @public
6743
- */
6744
- export interface SourceAlgorithmSpecification {
6745
- /**
6746
- * <p>A list of the algorithms that were used to create a model package.</p>
6747
- * @public
6748
- */
6749
- SourceAlgorithms: SourceAlgorithm[] | undefined;
6750
- }
6751
6797
  /**
6752
6798
  * @internal
6753
6799
  */