@aws-sdk/client-sagemaker 3.936.0 → 3.937.0

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 (63) hide show
  1. package/README.md +16 -0
  2. package/dist-cjs/index.js +333 -125
  3. package/dist-es/SageMaker.js +4 -0
  4. package/dist-es/commands/BatchRebootClusterNodesCommand.js +16 -0
  5. package/dist-es/commands/BatchReplaceClusterNodesCommand.js +16 -0
  6. package/dist-es/commands/index.js +2 -0
  7. package/dist-es/models/enums.js +43 -0
  8. package/dist-es/schemas/schemas_0.js +259 -125
  9. package/dist-types/SageMaker.d.ts +14 -0
  10. package/dist-types/SageMakerClient.d.ts +4 -2
  11. package/dist-types/commands/BatchRebootClusterNodesCommand.d.ts +102 -0
  12. package/dist-types/commands/BatchReplaceClusterNodesCommand.d.ts +102 -0
  13. package/dist-types/commands/CreateComputeQuotaCommand.d.ts +4 -0
  14. package/dist-types/commands/CreateDataQualityJobDefinitionCommand.d.ts +1 -1
  15. package/dist-types/commands/CreateDeviceFleetCommand.d.ts +1 -1
  16. package/dist-types/commands/CreateTrialComponentCommand.d.ts +1 -1
  17. package/dist-types/commands/CreateUserProfileCommand.d.ts +1 -1
  18. package/dist-types/commands/DescribeComputeQuotaCommand.d.ts +4 -0
  19. package/dist-types/commands/DescribeTrainingPlanCommand.d.ts +1 -1
  20. package/dist-types/commands/DescribeTrialComponentCommand.d.ts +2 -1
  21. package/dist-types/commands/DescribeUserProfileCommand.d.ts +1 -1
  22. package/dist-types/commands/DescribeWorkforceCommand.d.ts +1 -1
  23. package/dist-types/commands/ListClusterNodesCommand.d.ts +1 -0
  24. package/dist-types/commands/ListComputeQuotasCommand.d.ts +4 -0
  25. package/dist-types/commands/ListTrainingPlansCommand.d.ts +1 -1
  26. package/dist-types/commands/ListUltraServersByReservedCapacityCommand.d.ts +1 -1
  27. package/dist-types/commands/ListUserProfilesCommand.d.ts +1 -1
  28. package/dist-types/commands/ListWorkforcesCommand.d.ts +1 -1
  29. package/dist-types/commands/ListWorkteamsCommand.d.ts +1 -2
  30. package/dist-types/commands/SearchTrainingPlanOfferingsCommand.d.ts +2 -2
  31. package/dist-types/commands/UpdateComputeQuotaCommand.d.ts +4 -0
  32. package/dist-types/commands/index.d.ts +2 -0
  33. package/dist-types/models/enums.d.ts +67 -0
  34. package/dist-types/models/models_0.d.ts +201 -207
  35. package/dist-types/models/models_1.d.ts +208 -261
  36. package/dist-types/models/models_2.d.ts +263 -353
  37. package/dist-types/models/models_3.d.ts +354 -257
  38. package/dist-types/models/models_4.d.ts +259 -7
  39. package/dist-types/schemas/schemas_0.d.ts +15 -0
  40. package/dist-types/ts3.4/SageMaker.d.ts +34 -0
  41. package/dist-types/ts3.4/SageMakerClient.d.ts +12 -0
  42. package/dist-types/ts3.4/commands/BatchRebootClusterNodesCommand.d.ts +51 -0
  43. package/dist-types/ts3.4/commands/BatchReplaceClusterNodesCommand.d.ts +51 -0
  44. package/dist-types/ts3.4/commands/CreateDataQualityJobDefinitionCommand.d.ts +1 -1
  45. package/dist-types/ts3.4/commands/CreateDeviceFleetCommand.d.ts +1 -1
  46. package/dist-types/ts3.4/commands/CreateTrialComponentCommand.d.ts +1 -1
  47. package/dist-types/ts3.4/commands/CreateUserProfileCommand.d.ts +1 -1
  48. package/dist-types/ts3.4/commands/DescribeTrialComponentCommand.d.ts +2 -4
  49. package/dist-types/ts3.4/commands/DescribeUserProfileCommand.d.ts +1 -1
  50. package/dist-types/ts3.4/commands/DescribeWorkforceCommand.d.ts +1 -1
  51. package/dist-types/ts3.4/commands/ListUltraServersByReservedCapacityCommand.d.ts +1 -1
  52. package/dist-types/ts3.4/commands/ListUserProfilesCommand.d.ts +1 -1
  53. package/dist-types/ts3.4/commands/ListWorkforcesCommand.d.ts +1 -1
  54. package/dist-types/ts3.4/commands/ListWorkteamsCommand.d.ts +4 -2
  55. package/dist-types/ts3.4/commands/index.d.ts +2 -0
  56. package/dist-types/ts3.4/models/enums.d.ts +49 -0
  57. package/dist-types/ts3.4/models/models_0.d.ts +51 -50
  58. package/dist-types/ts3.4/models/models_1.d.ts +53 -83
  59. package/dist-types/ts3.4/models/models_2.d.ts +80 -88
  60. package/dist-types/ts3.4/models/models_3.d.ts +89 -68
  61. package/dist-types/ts3.4/models/models_4.d.ts +73 -8
  62. package/dist-types/ts3.4/schemas/schemas_0.d.ts +15 -0
  63. package/package.json +1 -1
@@ -1,3 +1,41 @@
1
+ /**
2
+ * @public
3
+ * @enum
4
+ */
5
+ export declare const MIGProfileType: {
6
+ readonly MIG_1G_10GB: "mig-1g.10gb";
7
+ readonly MIG_1G_18GB: "mig-1g.18gb";
8
+ readonly MIG_1G_20GB: "mig-1g.20gb";
9
+ readonly MIG_1G_23GB: "mig-1g.23gb";
10
+ readonly MIG_1G_35GB: "mig-1g.35gb";
11
+ readonly MIG_1G_45GB: "mig-1g.45gb";
12
+ readonly MIG_1G_47GB: "mig-1g.47gb";
13
+ readonly MIG_1G_5GB: "mig-1g.5gb";
14
+ readonly MIG_2G_10GB: "mig-2g.10gb";
15
+ readonly MIG_2G_20GB: "mig-2g.20gb";
16
+ readonly MIG_2G_35GB: "mig-2g.35gb";
17
+ readonly MIG_2G_45GB: "mig-2g.45gb";
18
+ readonly MIG_2G_47GB: "mig-2g.47gb";
19
+ readonly MIG_3G_20GB: "mig-3g.20gb";
20
+ readonly MIG_3G_40GB: "mig-3g.40gb";
21
+ readonly MIG_3G_71GB: "mig-3g.71gb";
22
+ readonly MIG_3G_90GB: "mig-3g.90gb";
23
+ readonly MIG_3G_93GB: "mig-3g.93gb";
24
+ readonly MIG_4G_20GB: "mig-4g.20gb";
25
+ readonly MIG_4G_40GB: "mig-4g.40gb";
26
+ readonly MIG_4G_71GB: "mig-4g.71gb";
27
+ readonly MIG_4G_90GB: "mig-4g.90gb";
28
+ readonly MIG_4G_93GB: "mig-4g.93gb";
29
+ readonly MIG_7G_141GB: "mig-7g.141gb";
30
+ readonly MIG_7G_180GB: "mig-7g.180gb";
31
+ readonly MIG_7G_186GB: "mig-7g.186gb";
32
+ readonly MIG_7G_40GB: "mig-7g.40gb";
33
+ readonly MIG_7G_80GB: "mig-7g.80gb";
34
+ };
35
+ /**
36
+ * @public
37
+ */
38
+ export type MIGProfileType = (typeof MIGProfileType)[keyof typeof MIGProfileType];
1
39
  /**
2
40
  * @public
3
41
  * @enum
@@ -1607,6 +1645,34 @@ export declare const ModelPackageStatus: {
1607
1645
  * @public
1608
1646
  */
1609
1647
  export type ModelPackageStatus = (typeof ModelPackageStatus)[keyof typeof ModelPackageStatus];
1648
+ /**
1649
+ * @public
1650
+ * @enum
1651
+ */
1652
+ export declare const BatchRebootClusterNodesErrorCode: {
1653
+ readonly INSTANCE_ID_IN_USE: "InstanceIdInUse";
1654
+ readonly INSTANCE_ID_NOT_FOUND: "InstanceIdNotFound";
1655
+ readonly INTERNAL_SERVER_ERROR: "InternalServerError";
1656
+ readonly INVALID_INSTANCE_STATUS: "InvalidInstanceStatus";
1657
+ };
1658
+ /**
1659
+ * @public
1660
+ */
1661
+ export type BatchRebootClusterNodesErrorCode = (typeof BatchRebootClusterNodesErrorCode)[keyof typeof BatchRebootClusterNodesErrorCode];
1662
+ /**
1663
+ * @public
1664
+ * @enum
1665
+ */
1666
+ export declare const BatchReplaceClusterNodesErrorCode: {
1667
+ readonly INSTANCE_ID_IN_USE: "InstanceIdInUse";
1668
+ readonly INSTANCE_ID_NOT_FOUND: "InstanceIdNotFound";
1669
+ readonly INTERNAL_SERVER_ERROR: "InternalServerError";
1670
+ readonly INVALID_INSTANCE_STATUS: "InvalidInstanceStatus";
1671
+ };
1672
+ /**
1673
+ * @public
1674
+ */
1675
+ export type BatchReplaceClusterNodesErrorCode = (typeof BatchReplaceClusterNodesErrorCode)[keyof typeof BatchReplaceClusterNodesErrorCode];
1610
1676
  /**
1611
1677
  * @public
1612
1678
  * @enum
@@ -4417,6 +4483,7 @@ export type TrainingPlanStatus = (typeof TrainingPlanStatus)[keyof typeof Traini
4417
4483
  * @enum
4418
4484
  */
4419
4485
  export declare const SageMakerResourceName: {
4486
+ readonly ENDPOINT: "endpoint";
4420
4487
  readonly HYPERPOD_CLUSTER: "hyperpod-cluster";
4421
4488
  readonly TRAINING_JOB: "training-job";
4422
4489
  };
@@ -1,4 +1,20 @@
1
- import { ActionStatus, ActivationState, 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, BatchStrategy, CandidateStatus, CandidateStepType, CapacityReservationType, CapacitySizeType, CaptureMode, ClarifyFeatureType, ClarifyTextGranularity, ClarifyTextLanguage, ClusterAutoScalerType, ClusterAutoScalingMode, ClusterAutoScalingStatus, ClusterConfigMode, ClusterEventResourceType, ClusterInstanceStatus, ClusterInstanceType, ClusterNodeProvisioningMode, ClusterNodeRecovery, ClusterStatus, CompilationJobStatus, CompleteOnConvergence, CompressionType, ConditionOutcome, ContainerMode, DataSourceName, DeepHealthCheckType, DetailedAlgorithmStatus, EdgePresetDeploymentType, FairShare, FeatureStatus, FileSystemAccessMode, FileSystemType, FillingType, Framework, HyperParameterScalingType, HyperParameterTuningJobObjectiveType, InstanceGroupStatus, LifecycleManagement, MetricSetSource, ModelApprovalStatus, ModelCacheSetting, ModelCompressionType, ModelPackageStatus, NodeUnavailabilityType, ObjectiveStatus, OutputCompressionType, ParameterType, PreemptTeamTasks, ProblemType, ProcessingInstanceType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProcessingS3UploadMode, ProductionVariantInstanceType, RecordWrapper, RepositoryAccessMode, ResourceSharingStrategy, S3DataDistribution, S3DataType, S3ModelDataType, SchedulerResourceStatus, SoftwareUpdateStatus, SplitType, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrafficRoutingConfigType, TrainingInputMode, TrainingInstanceType, TrainingRepositoryAccessMode, TransformInstanceType, VolumeAttachmentStatus } from "./enums";
1
+ import { ActionStatus, ActivationState, 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, ClusterConfigMode, ClusterEventResourceType, ClusterInstanceStatus, ClusterInstanceType, ClusterNodeProvisioningMode, ClusterNodeRecovery, ClusterStatus, CompilationJobStatus, CompleteOnConvergence, CompressionType, ConditionOutcome, ContainerMode, DataSourceName, DeepHealthCheckType, DetailedAlgorithmStatus, FairShare, FeatureStatus, FileSystemAccessMode, FileSystemType, FillingType, Framework, HyperParameterScalingType, HyperParameterTuningJobObjectiveType, InstanceGroupStatus, LifecycleManagement, MetricSetSource, MIGProfileType, ModelApprovalStatus, ModelCacheSetting, ModelCompressionType, ModelPackageStatus, NodeUnavailabilityType, ObjectiveStatus, OutputCompressionType, ParameterType, PreemptTeamTasks, ProblemType, ProcessingInstanceType, ProcessingS3DataDistributionType, ProcessingS3InputMode, ProcessingS3UploadMode, ProductionVariantInstanceType, RecordWrapper, RepositoryAccessMode, ResourceSharingStrategy, S3DataDistribution, S3DataType, S3ModelDataType, SchedulerResourceStatus, SoftwareUpdateStatus, SplitType, TargetDevice, TargetPlatformAccelerator, TargetPlatformArch, TargetPlatformOs, TrafficRoutingConfigType, TrainingInputMode, TrainingInstanceType, TrainingRepositoryAccessMode, TransformInstanceType, VolumeAttachmentStatus } from "./enums";
2
+ /**
3
+ * <p>Configuration for allocating accelerator partitions.</p>
4
+ * @public
5
+ */
6
+ export interface AcceleratorPartitionConfig {
7
+ /**
8
+ * <p>The Multi-Instance GPU (MIG) profile type that defines the partition configuration. The profile specifies the compute and memory allocation for each partition instance. The available profile types depend on the instance type specified in the compute quota configuration.</p>
9
+ * @public
10
+ */
11
+ Type: MIGProfileType | undefined;
12
+ /**
13
+ * <p>The number of accelerator partitions to allocate with the specified partition type. If you don't specify a value for vCPU and MemoryInGiB, SageMaker AI automatically allocates ratio-based values for those parameters based on the accelerator partition count you provide.</p>
14
+ * @public
15
+ */
16
+ Count: number | undefined;
17
+ }
2
18
  /**
3
19
  * <p>A structure describing the source of an action.</p>
4
20
  * @public
@@ -3118,6 +3134,180 @@ export interface BatchDescribeModelPackageOutput {
3118
3134
  */
3119
3135
  BatchDescribeModelPackageErrorMap?: Record<string, BatchDescribeModelPackageError> | undefined;
3120
3136
  }
3137
+ /**
3138
+ * <p>Represents an error encountered when rebooting a node (identified by its logical node ID) from a SageMaker HyperPod cluster.</p>
3139
+ * @public
3140
+ */
3141
+ export interface BatchRebootClusterNodeLogicalIdsError {
3142
+ /**
3143
+ * <p>The logical node ID of the node that encountered an error during the reboot operation.</p>
3144
+ * @public
3145
+ */
3146
+ NodeLogicalId: string | undefined;
3147
+ /**
3148
+ * <p>The error code associated with the error encountered when rebooting a node by logical node ID.</p> <p>Possible values:</p> <ul> <li> <p> <code>InstanceIdNotFound</code>: The node does not exist in the specified cluster.</p> </li> <li> <p> <code>InvalidInstanceStatus</code>: The node is in a state that does not allow rebooting. Wait for the node to finish any ongoing changes before retrying.</p> </li> <li> <p> <code>InstanceIdInUse</code>: Another operation is already in progress for this node. Wait for the operation to complete before retrying.</p> </li> <li> <p> <code>InternalServerError</code>: An internal error occurred while processing this node.</p> </li> </ul>
3149
+ * @public
3150
+ */
3151
+ ErrorCode: BatchRebootClusterNodesErrorCode | undefined;
3152
+ /**
3153
+ * <p>A human-readable message describing the error encountered when rebooting a node by logical node ID.</p>
3154
+ * @public
3155
+ */
3156
+ Message: string | undefined;
3157
+ }
3158
+ /**
3159
+ * @public
3160
+ */
3161
+ export interface BatchRebootClusterNodesRequest {
3162
+ /**
3163
+ * <p>The name or Amazon Resource Name (ARN) of the SageMaker HyperPod cluster containing the nodes to reboot.</p>
3164
+ * @public
3165
+ */
3166
+ ClusterName: string | undefined;
3167
+ /**
3168
+ * <p>A list of EC2 instance IDs to reboot using soft recovery. You can specify between 1 and 25 instance IDs.</p> <note> <ul> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> <li> <p>Each instance ID must follow the pattern <code>i-</code> followed by 17 hexadecimal characters (for example, <code>i-0123456789abcdef0</code>).</p> </li> </ul> </note>
3169
+ * @public
3170
+ */
3171
+ NodeIds?: string[] | undefined;
3172
+ /**
3173
+ * <p>A list of logical node IDs to reboot using soft recovery. You can specify between 1 and 25 logical node IDs.</p> <p>The <code>NodeLogicalId</code> is a unique identifier that persists throughout the node's lifecycle and can be used to track nodes that are still being provisioned and don't yet have an EC2 instance ID assigned.</p> <important> <ul> <li> <p>This parameter is only supported for clusters using <code>Continuous</code> as the <code>NodeProvisioningMode</code>. For clusters using the default provisioning mode, use <code>NodeIds</code> instead.</p> </li> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> </ul> </important>
3174
+ * @public
3175
+ */
3176
+ NodeLogicalIds?: string[] | undefined;
3177
+ }
3178
+ /**
3179
+ * <p>Represents an error encountered when rebooting a node from a SageMaker HyperPod cluster.</p>
3180
+ * @public
3181
+ */
3182
+ export interface BatchRebootClusterNodesError {
3183
+ /**
3184
+ * <p>The EC2 instance ID of the node that encountered an error during the reboot operation.</p>
3185
+ * @public
3186
+ */
3187
+ NodeId: string | undefined;
3188
+ /**
3189
+ * <p>The error code associated with the error encountered when rebooting a node.</p> <p>Possible values:</p> <ul> <li> <p> <code>InstanceIdNotFound</code>: The instance does not exist in the specified cluster.</p> </li> <li> <p> <code>InvalidInstanceStatus</code>: The instance is in a state that does not allow rebooting. Wait for the instance to finish any ongoing changes before retrying.</p> </li> <li> <p> <code>InstanceIdInUse</code>: Another operation is already in progress for this node. Wait for the operation to complete before retrying.</p> </li> <li> <p> <code>InternalServerError</code>: An internal error occurred while processing this node.</p> </li> </ul>
3190
+ * @public
3191
+ */
3192
+ ErrorCode: BatchRebootClusterNodesErrorCode | undefined;
3193
+ /**
3194
+ * <p>A human-readable message describing the error encountered when rebooting a node.</p>
3195
+ * @public
3196
+ */
3197
+ Message: string | undefined;
3198
+ }
3199
+ /**
3200
+ * @public
3201
+ */
3202
+ export interface BatchRebootClusterNodesResponse {
3203
+ /**
3204
+ * <p>A list of EC2 instance IDs for which the reboot operation was successfully initiated.</p>
3205
+ * @public
3206
+ */
3207
+ Successful?: string[] | undefined;
3208
+ /**
3209
+ * <p>A list of errors encountered for EC2 instance IDs that could not be rebooted. Each error includes the instance ID, an error code, and a descriptive message.</p>
3210
+ * @public
3211
+ */
3212
+ Failed?: BatchRebootClusterNodesError[] | undefined;
3213
+ /**
3214
+ * <p>A list of errors encountered for logical node IDs that could not be rebooted. Each error includes the logical node ID, an error code, and a descriptive message. This field is only present when <code>NodeLogicalIds</code> were provided in the request.</p>
3215
+ * @public
3216
+ */
3217
+ FailedNodeLogicalIds?: BatchRebootClusterNodeLogicalIdsError[] | undefined;
3218
+ /**
3219
+ * <p>A list of logical node IDs for which the reboot operation was successfully initiated. This field is only present when <code>NodeLogicalIds</code> were provided in the request.</p>
3220
+ * @public
3221
+ */
3222
+ SuccessfulNodeLogicalIds?: string[] | undefined;
3223
+ }
3224
+ /**
3225
+ * <p>Represents an error encountered when replacing a node (identified by its logical node ID) in a SageMaker HyperPod cluster.</p>
3226
+ * @public
3227
+ */
3228
+ export interface BatchReplaceClusterNodeLogicalIdsError {
3229
+ /**
3230
+ * <p>The logical node ID of the node that encountered an error during the replacement operation.</p>
3231
+ * @public
3232
+ */
3233
+ NodeLogicalId: string | undefined;
3234
+ /**
3235
+ * <p>The error code associated with the error encountered when replacing a node by logical node ID.</p> <p>Possible values:</p> <ul> <li> <p> <code>InstanceIdNotFound</code>: The node does not exist in the specified cluster.</p> </li> <li> <p> <code>InvalidInstanceStatus</code>: The node is in a state that does not allow replacement. Wait for the node to finish any ongoing changes before retrying.</p> </li> <li> <p> <code>InstanceIdInUse</code>: Another operation is already in progress for this node. Wait for the operation to complete before retrying.</p> </li> <li> <p> <code>InternalServerError</code>: An internal error occurred while processing this node.</p> </li> </ul>
3236
+ * @public
3237
+ */
3238
+ ErrorCode: BatchReplaceClusterNodesErrorCode | undefined;
3239
+ /**
3240
+ * <p>A human-readable message describing the error encountered when replacing a node by logical node ID.</p>
3241
+ * @public
3242
+ */
3243
+ Message: string | undefined;
3244
+ }
3245
+ /**
3246
+ * @public
3247
+ */
3248
+ export interface BatchReplaceClusterNodesRequest {
3249
+ /**
3250
+ * <p>The name or Amazon Resource Name (ARN) of the SageMaker HyperPod cluster containing the nodes to replace.</p>
3251
+ * @public
3252
+ */
3253
+ ClusterName: string | undefined;
3254
+ /**
3255
+ * <p>A list of EC2 instance IDs to replace with new hardware. You can specify between 1 and 25 instance IDs.</p> <important> <p>Replace operations destroy all instance volumes (root and secondary). Ensure you have backed up any important data before proceeding.</p> </important> <note> <ul> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> <li> <p>Each instance ID must follow the pattern <code>i-</code> followed by 17 hexadecimal characters (for example, <code>i-0123456789abcdef0</code>).</p> </li> <li> <p>For SageMaker HyperPod clusters using the Slurm workload manager, you cannot replace instances that are configured as Slurm controller nodes.</p> </li> </ul> </note>
3256
+ * @public
3257
+ */
3258
+ NodeIds?: string[] | undefined;
3259
+ /**
3260
+ * <p>A list of logical node IDs to replace with new hardware. You can specify between 1 and 25 logical node IDs.</p> <p>The <code>NodeLogicalId</code> is a unique identifier that persists throughout the node's lifecycle and can be used to track nodes that are still being provisioned and don't yet have an EC2 instance ID assigned.</p> <important> <ul> <li> <p>Replace operations destroy all instance volumes (root and secondary). Ensure you have backed up any important data before proceeding.</p> </li> <li> <p>This parameter is only supported for clusters using <code>Continuous</code> as the <code>NodeProvisioningMode</code>. For clusters using the default provisioning mode, use <code>NodeIds</code> instead.</p> </li> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> </ul> </important>
3261
+ * @public
3262
+ */
3263
+ NodeLogicalIds?: string[] | undefined;
3264
+ }
3265
+ /**
3266
+ * <p>Represents an error encountered when replacing a node in a SageMaker HyperPod cluster.</p>
3267
+ * @public
3268
+ */
3269
+ export interface BatchReplaceClusterNodesError {
3270
+ /**
3271
+ * <p>The EC2 instance ID of the node that encountered an error during the replacement operation.</p>
3272
+ * @public
3273
+ */
3274
+ NodeId: string | undefined;
3275
+ /**
3276
+ * <p>The error code associated with the error encountered when replacing a node.</p> <p>Possible values:</p> <ul> <li> <p> <code>InstanceIdNotFound</code>: The instance does not exist in the specified cluster.</p> </li> <li> <p> <code>InvalidInstanceStatus</code>: The instance is in a state that does not allow replacement. Wait for the instance to finish any ongoing changes before retrying.</p> </li> <li> <p> <code>InstanceIdInUse</code>: Another operation is already in progress for this node. Wait for the operation to complete before retrying.</p> </li> <li> <p> <code>InternalServerError</code>: An internal error occurred while processing this node.</p> </li> </ul>
3277
+ * @public
3278
+ */
3279
+ ErrorCode: BatchReplaceClusterNodesErrorCode | undefined;
3280
+ /**
3281
+ * <p>A human-readable message describing the error encountered when replacing a node.</p>
3282
+ * @public
3283
+ */
3284
+ Message: string | undefined;
3285
+ }
3286
+ /**
3287
+ * @public
3288
+ */
3289
+ export interface BatchReplaceClusterNodesResponse {
3290
+ /**
3291
+ * <p>A list of EC2 instance IDs for which the replacement operation was successfully initiated.</p>
3292
+ * @public
3293
+ */
3294
+ Successful?: string[] | undefined;
3295
+ /**
3296
+ * <p>A list of errors encountered for EC2 instance IDs that could not be replaced. Each error includes the instance ID, an error code, and a descriptive message.</p>
3297
+ * @public
3298
+ */
3299
+ Failed?: BatchReplaceClusterNodesError[] | undefined;
3300
+ /**
3301
+ * <p>A list of errors encountered for logical node IDs that could not be replaced. Each error includes the logical node ID, an error code, and a descriptive message. This field is only present when <code>NodeLogicalIds</code> were provided in the request.</p>
3302
+ * @public
3303
+ */
3304
+ FailedNodeLogicalIds?: BatchReplaceClusterNodeLogicalIdsError[] | undefined;
3305
+ /**
3306
+ * <p>A list of logical node IDs for which the replacement operation was successfully initiated. This field is only present when <code>NodeLogicalIds</code> were provided in the request.</p>
3307
+ * @public
3308
+ */
3309
+ SuccessfulNodeLogicalIds?: string[] | undefined;
3310
+ }
3121
3311
  /**
3122
3312
  * <p>Represents the CSV dataset format used when running a monitoring job.</p>
3123
3313
  * @public
@@ -4871,6 +5061,11 @@ export interface ClusterNodeSummary {
4871
5061
  * @public
4872
5062
  */
4873
5063
  UltraServerInfo?: UltraServerInfo | undefined;
5064
+ /**
5065
+ * <p>The private DNS hostname of the SageMaker HyperPod cluster node.</p>
5066
+ * @public
5067
+ */
5068
+ PrivateDnsHostname?: string | undefined;
4874
5069
  }
4875
5070
  /**
4876
5071
  * <p>The configuration settings for the Amazon EKS cluster used as the orchestrator for the SageMaker HyperPod cluster.</p>
@@ -5470,6 +5665,11 @@ export interface ComputeQuotaResourceConfig {
5470
5665
  * @public
5471
5666
  */
5472
5667
  MemoryInGiB?: number | undefined;
5668
+ /**
5669
+ * <p>The accelerator partition configuration for fractional GPU allocation.</p>
5670
+ * @public
5671
+ */
5672
+ AcceleratorPartition?: AcceleratorPartitionConfig | undefined;
5473
5673
  }
5474
5674
  /**
5475
5675
  * <p>Resource sharing configuration.</p>
@@ -7039,209 +7239,3 @@ export interface MonitoringResources {
7039
7239
  */
7040
7240
  ClusterConfig: MonitoringClusterConfig | undefined;
7041
7241
  }
7042
- /**
7043
- * <p>The networking configuration for the monitoring job.</p>
7044
- * @public
7045
- */
7046
- export interface MonitoringNetworkConfig {
7047
- /**
7048
- * <p>Whether to encrypt all communications between the instances used for the monitoring jobs. Choose <code>True</code> to encrypt communications. Encryption provides greater security for distributed jobs, but the processing might take longer.</p>
7049
- * @public
7050
- */
7051
- EnableInterContainerTrafficEncryption?: boolean | undefined;
7052
- /**
7053
- * <p>Whether to allow inbound and outbound network calls to and from the containers used for the monitoring job.</p>
7054
- * @public
7055
- */
7056
- EnableNetworkIsolation?: boolean | undefined;
7057
- /**
7058
- * <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>
7059
- * @public
7060
- */
7061
- VpcConfig?: VpcConfig | undefined;
7062
- }
7063
- /**
7064
- * <p>A time limit for how long the monitoring job is allowed to run before stopping.</p>
7065
- * @public
7066
- */
7067
- export interface MonitoringStoppingCondition {
7068
- /**
7069
- * <p>The maximum runtime allowed in seconds.</p> <note> <p>The <code>MaxRuntimeInSeconds</code> cannot exceed the frequency of the job. For data quality and model explainability, this can be up to 3600 seconds for an hourly schedule. For model bias and model quality hourly schedules, this can be up to 1800 seconds.</p> </note>
7070
- * @public
7071
- */
7072
- MaxRuntimeInSeconds: number | undefined;
7073
- }
7074
- /**
7075
- * @public
7076
- */
7077
- export interface CreateDataQualityJobDefinitionRequest {
7078
- /**
7079
- * <p>The name for the monitoring job definition.</p>
7080
- * @public
7081
- */
7082
- JobDefinitionName: string | undefined;
7083
- /**
7084
- * <p>Configures the constraints and baselines for the monitoring job.</p>
7085
- * @public
7086
- */
7087
- DataQualityBaselineConfig?: DataQualityBaselineConfig | undefined;
7088
- /**
7089
- * <p>Specifies the container that runs the monitoring job.</p>
7090
- * @public
7091
- */
7092
- DataQualityAppSpecification: DataQualityAppSpecification | undefined;
7093
- /**
7094
- * <p>A list of inputs for the monitoring job. Currently endpoints are supported as monitoring inputs.</p>
7095
- * @public
7096
- */
7097
- DataQualityJobInput: DataQualityJobInput | undefined;
7098
- /**
7099
- * <p>The output configuration for monitoring jobs.</p>
7100
- * @public
7101
- */
7102
- DataQualityJobOutputConfig: MonitoringOutputConfig | undefined;
7103
- /**
7104
- * <p>Identifies the resources to deploy for a monitoring job.</p>
7105
- * @public
7106
- */
7107
- JobResources: MonitoringResources | undefined;
7108
- /**
7109
- * <p>Specifies networking configuration for the monitoring job.</p>
7110
- * @public
7111
- */
7112
- NetworkConfig?: MonitoringNetworkConfig | undefined;
7113
- /**
7114
- * <p>The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform tasks on your behalf.</p>
7115
- * @public
7116
- */
7117
- RoleArn: string | undefined;
7118
- /**
7119
- * <p>A time limit for how long the monitoring job is allowed to run before stopping.</p>
7120
- * @public
7121
- */
7122
- StoppingCondition?: MonitoringStoppingCondition | undefined;
7123
- /**
7124
- * <p>(Optional) An array of key-value pairs. For more information, see <a href="https://docs.aws.amazon.com/awsaccountbilling/latest/aboutv2/cost-alloc-tags.html#allocation-whatURL"> Using Cost Allocation Tags</a> in the <i>Amazon Web Services Billing and Cost Management User Guide</i>.</p>
7125
- * @public
7126
- */
7127
- Tags?: Tag[] | undefined;
7128
- }
7129
- /**
7130
- * @public
7131
- */
7132
- export interface CreateDataQualityJobDefinitionResponse {
7133
- /**
7134
- * <p>The Amazon Resource Name (ARN) of the job definition.</p>
7135
- * @public
7136
- */
7137
- JobDefinitionArn: string | undefined;
7138
- }
7139
- /**
7140
- * <p>The output configuration.</p>
7141
- * @public
7142
- */
7143
- export interface EdgeOutputConfig {
7144
- /**
7145
- * <p>The Amazon Simple Storage (S3) bucker URI.</p>
7146
- * @public
7147
- */
7148
- S3OutputLocation: string | undefined;
7149
- /**
7150
- * <p>The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt data on the storage volume after compilation job. If you don't provide a KMS key ID, Amazon SageMaker uses the default KMS key for Amazon S3 for your role's account.</p>
7151
- * @public
7152
- */
7153
- KmsKeyId?: string | undefined;
7154
- /**
7155
- * <p>The deployment type SageMaker Edge Manager will create. Currently only supports Amazon Web Services IoT Greengrass Version 2 components.</p>
7156
- * @public
7157
- */
7158
- PresetDeploymentType?: EdgePresetDeploymentType | undefined;
7159
- /**
7160
- * <p>The configuration used to create deployment artifacts. Specify configuration options with a JSON string. The available configuration options for each type are:</p> <ul> <li> <p> <code>ComponentName</code> (optional) - Name of the GreenGrass V2 component. If not specified, the default name generated consists of "SagemakerEdgeManager" and the name of your SageMaker Edge Manager packaging job.</p> </li> <li> <p> <code>ComponentDescription</code> (optional) - Description of the component.</p> </li> <li> <p> <code>ComponentVersion</code> (optional) - The version of the component.</p> <note> <p>Amazon Web Services IoT Greengrass uses semantic versions for components. Semantic versions follow a<i> major.minor.patch</i> number system. For example, version 1.0.0 represents the first major release for a component. For more information, see the <a href="https://semver.org/">semantic version specification</a>.</p> </note> </li> <li> <p> <code>PlatformOS</code> (optional) - The name of the operating system for the platform. Supported platforms include Windows and Linux.</p> </li> <li> <p> <code>PlatformArchitecture</code> (optional) - The processor architecture for the platform. </p> <p>Supported architectures Windows include: Windows32_x86, Windows64_x64.</p> <p>Supported architectures for Linux include: Linux x86_64, Linux ARMV8.</p> </li> </ul>
7161
- * @public
7162
- */
7163
- PresetDeploymentConfig?: string | undefined;
7164
- }
7165
- /**
7166
- * @public
7167
- */
7168
- export interface CreateDeviceFleetRequest {
7169
- /**
7170
- * <p>The name of the fleet that the device belongs to.</p>
7171
- * @public
7172
- */
7173
- DeviceFleetName: string | undefined;
7174
- /**
7175
- * <p>The Amazon Resource Name (ARN) that has access to Amazon Web Services Internet of Things (IoT).</p>
7176
- * @public
7177
- */
7178
- RoleArn?: string | undefined;
7179
- /**
7180
- * <p>A description of the fleet.</p>
7181
- * @public
7182
- */
7183
- Description?: string | undefined;
7184
- /**
7185
- * <p>The output configuration for storing sample data collected by the fleet.</p>
7186
- * @public
7187
- */
7188
- OutputConfig: EdgeOutputConfig | undefined;
7189
- /**
7190
- * <p>Creates tags for the specified fleet.</p>
7191
- * @public
7192
- */
7193
- Tags?: Tag[] | undefined;
7194
- /**
7195
- * <p>Whether to create an Amazon Web Services IoT Role Alias during device fleet creation. The name of the role alias generated will match this pattern: "SageMakerEdge-\{DeviceFleetName\}".</p> <p>For example, if your device fleet is called "demo-fleet", the name of the role alias will be "SageMakerEdge-demo-fleet".</p>
7196
- * @public
7197
- */
7198
- EnableIotRoleAlias?: boolean | undefined;
7199
- }
7200
- /**
7201
- * <p>The settings for assigning a custom Amazon EFS file system to a user profile or space for an Amazon SageMaker AI Domain.</p>
7202
- * @public
7203
- */
7204
- export interface EFSFileSystemConfig {
7205
- /**
7206
- * <p>The ID of your Amazon EFS file system.</p>
7207
- * @public
7208
- */
7209
- FileSystemId: string | undefined;
7210
- /**
7211
- * <p>The path to the file system directory that is accessible in Amazon SageMaker AI Studio. Permitted users can access only this directory and below.</p>
7212
- * @public
7213
- */
7214
- FileSystemPath?: string | undefined;
7215
- }
7216
- /**
7217
- * <p>The settings for assigning a custom Amazon FSx for Lustre file system to a user profile or space for an Amazon SageMaker Domain.</p>
7218
- * @public
7219
- */
7220
- export interface FSxLustreFileSystemConfig {
7221
- /**
7222
- * <p>The globally unique, 17-digit, ID of the file system, assigned by Amazon FSx for Lustre.</p>
7223
- * @public
7224
- */
7225
- FileSystemId: string | undefined;
7226
- /**
7227
- * <p>The path to the file system directory that is accessible in Amazon SageMaker Studio. Permitted users can access only this directory and below.</p>
7228
- * @public
7229
- */
7230
- FileSystemPath?: string | undefined;
7231
- }
7232
- /**
7233
- * <p>Configuration for the custom Amazon S3 file system.</p>
7234
- * @public
7235
- */
7236
- export interface S3FileSystemConfig {
7237
- /**
7238
- * <p>The file system path where the Amazon S3 storage location will be mounted within the Amazon SageMaker Studio environment.</p>
7239
- * @public
7240
- */
7241
- MountPath?: string | undefined;
7242
- /**
7243
- * <p>The Amazon S3 URI of the S3 file system configuration.</p>
7244
- * @public
7245
- */
7246
- S3Uri: string | undefined;
7247
- }