sagemaker-core 1.0.48__py3-none-any.whl → 1.0.50__py3-none-any.whl

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.

Potentially problematic release.


This version of sagemaker-core might be problematic. Click here for more details.

@@ -494,6 +494,21 @@ class ActionSummary(Base):
494
494
  last_modified_time: Optional[datetime.datetime] = Unassigned()
495
495
 
496
496
 
497
+ class AddClusterNodeSpecification(Base):
498
+ """
499
+ AddClusterNodeSpecification
500
+ Specifies an instance group and the number of nodes to add to it.
501
+
502
+ Attributes
503
+ ----------------------
504
+ instance_group_name: The name of the instance group to which you want to add nodes.
505
+ increment_target_count_by: The number of nodes to add to the specified instance group. The total number of nodes across all instance groups in a single request cannot exceed 50.
506
+ """
507
+
508
+ instance_group_name: str
509
+ increment_target_count_by: int
510
+
511
+
497
512
  class Tag(Base):
498
513
  """
499
514
  Tag
@@ -509,6 +524,19 @@ class Tag(Base):
509
524
  value: str
510
525
 
511
526
 
527
+ class AdditionalEnis(Base):
528
+ """
529
+ AdditionalEnis
530
+ Information about additional Elastic Network Interfaces (ENIs) associated with an instance.
531
+
532
+ Attributes
533
+ ----------------------
534
+ efa_enis: A list of Elastic Fabric Adapter (EFA) ENIs associated with the instance.
535
+ """
536
+
537
+ efa_enis: Optional[List[str]] = Unassigned()
538
+
539
+
512
540
  class ModelAccessConfig(Base):
513
541
  """
514
542
  ModelAccessConfig
@@ -992,6 +1020,36 @@ class InstanceGroup(Base):
992
1020
  instance_group_name: str
993
1021
 
994
1022
 
1023
+ class PlacementSpecification(Base):
1024
+ """
1025
+ PlacementSpecification
1026
+ Specifies how instances should be placed on a specific UltraServer.
1027
+
1028
+ Attributes
1029
+ ----------------------
1030
+ ultra_server_id: The unique identifier of the UltraServer where instances should be placed.
1031
+ instance_count: The number of ML compute instances required to be placed together on the same UltraServer. Minimum value of 1.
1032
+ """
1033
+
1034
+ instance_count: int
1035
+ ultra_server_id: Optional[str] = Unassigned()
1036
+
1037
+
1038
+ class InstancePlacementConfig(Base):
1039
+ """
1040
+ InstancePlacementConfig
1041
+ Configuration for how instances are placed and allocated within UltraServers. This is only applicable for UltraServer capacity.
1042
+
1043
+ Attributes
1044
+ ----------------------
1045
+ enable_multiple_jobs: If set to true, allows multiple jobs to share the same UltraServer instances. If set to false, ensures this job's instances are placed on an UltraServer exclusively, with no other jobs sharing the same UltraServer. Default is false.
1046
+ placement_specifications: A list of specifications for how instances should be placed on specific UltraServers. Maximum of 10 items is supported.
1047
+ """
1048
+
1049
+ enable_multiple_jobs: Optional[bool] = Unassigned()
1050
+ placement_specifications: Optional[List[PlacementSpecification]] = Unassigned()
1051
+
1052
+
995
1053
  class ResourceConfig(Base):
996
1054
  """
997
1055
  ResourceConfig
@@ -1006,6 +1064,7 @@ class ResourceConfig(Base):
1006
1064
  keep_alive_period_in_seconds: The duration of time in seconds to retain configured resources in a warm pool for subsequent training jobs.
1007
1065
  instance_groups: The configuration of a heterogeneous cluster in JSON format.
1008
1066
  training_plan_arn: The Amazon Resource Name (ARN); of the training plan to use for this resource configuration.
1067
+ instance_placement_config: Configuration for how training job instances are placed and allocated within UltraServers. Only applicable for UltraServer capacity.
1009
1068
  """
1010
1069
 
1011
1070
  volume_size_in_gb: int
@@ -1015,6 +1074,7 @@ class ResourceConfig(Base):
1015
1074
  keep_alive_period_in_seconds: Optional[int] = Unassigned()
1016
1075
  instance_groups: Optional[List[InstanceGroup]] = Unassigned()
1017
1076
  training_plan_arn: Optional[str] = Unassigned()
1077
+ instance_placement_config: Optional[InstancePlacementConfig] = Unassigned()
1018
1078
 
1019
1079
 
1020
1080
  class StoppingCondition(Base):
@@ -2400,6 +2460,42 @@ class Autotune(Base):
2400
2460
  mode: str
2401
2461
 
2402
2462
 
2463
+ class BatchAddClusterNodesError(Base):
2464
+ """
2465
+ BatchAddClusterNodesError
2466
+ Information about an error that occurred during the node addition operation.
2467
+
2468
+ Attributes
2469
+ ----------------------
2470
+ instance_group_name: The name of the instance group for which the error occurred.
2471
+ error_code: The error code associated with the failure. Possible values include InstanceGroupNotFound and InvalidInstanceGroupState.
2472
+ failed_count: The number of nodes that failed to be added to the specified instance group.
2473
+ message: A descriptive message providing additional details about the error.
2474
+ """
2475
+
2476
+ instance_group_name: str
2477
+ error_code: str
2478
+ failed_count: int
2479
+ message: Optional[str] = Unassigned()
2480
+
2481
+
2482
+ class NodeAdditionResult(Base):
2483
+ """
2484
+ NodeAdditionResult
2485
+ Information about a node that was successfully added to the cluster.
2486
+
2487
+ Attributes
2488
+ ----------------------
2489
+ node_logical_id: A unique identifier assigned to the node that can be used to track its provisioning status through the DescribeClusterNode operation.
2490
+ instance_group_name: The name of the instance group to which the node was added.
2491
+ status: The current status of the node. Possible values include Pending, Running, Failed, ShuttingDown, SystemUpdating, DeepHealthCheckInProgress, and NotFound.
2492
+ """
2493
+
2494
+ node_logical_id: str
2495
+ instance_group_name: str
2496
+ status: str
2497
+
2498
+
2403
2499
  class BatchDataCaptureConfig(Base):
2404
2500
  """
2405
2501
  BatchDataCaptureConfig
@@ -2417,6 +2513,23 @@ class BatchDataCaptureConfig(Base):
2417
2513
  generate_inference_id: Optional[bool] = Unassigned()
2418
2514
 
2419
2515
 
2516
+ class BatchDeleteClusterNodeLogicalIdsError(Base):
2517
+ """
2518
+ BatchDeleteClusterNodeLogicalIdsError
2519
+ Information about an error that occurred when attempting to delete a node identified by its NodeLogicalId.
2520
+
2521
+ Attributes
2522
+ ----------------------
2523
+ code: The error code associated with the failure. Possible values include NodeLogicalIdNotFound, InvalidNodeStatus, and InternalError.
2524
+ message: A descriptive message providing additional details about the error.
2525
+ node_logical_id: The NodeLogicalId of the node that could not be deleted.
2526
+ """
2527
+
2528
+ code: str
2529
+ message: str
2530
+ node_logical_id: str
2531
+
2532
+
2420
2533
  class BatchDeleteClusterNodesError(Base):
2421
2534
  """
2422
2535
  BatchDeleteClusterNodesError
@@ -2442,10 +2555,14 @@ class BatchDeleteClusterNodesResponse(Base):
2442
2555
  ----------------------
2443
2556
  failed: A list of errors encountered when deleting the specified nodes.
2444
2557
  successful: A list of node IDs that were successfully deleted from the specified cluster.
2558
+ failed_node_logical_ids: A list of NodeLogicalIds that could not be deleted, along with error information explaining why the deletion failed.
2559
+ successful_node_logical_ids: A list of NodeLogicalIds that were successfully deleted from the cluster.
2445
2560
  """
2446
2561
 
2447
2562
  failed: Optional[List[BatchDeleteClusterNodesError]] = Unassigned()
2448
2563
  successful: Optional[List[str]] = Unassigned()
2564
+ failed_node_logical_ids: Optional[List[BatchDeleteClusterNodeLogicalIdsError]] = Unassigned()
2565
+ successful_node_logical_ids: Optional[List[str]] = Unassigned()
2449
2566
 
2450
2567
 
2451
2568
  class BatchDescribeModelPackageError(Base):
@@ -2901,6 +3018,21 @@ class CanvasAppSettings(Base):
2901
3018
  emr_serverless_settings: Optional[EmrServerlessSettings] = Unassigned()
2902
3019
 
2903
3020
 
3021
+ class CapacityReservation(Base):
3022
+ """
3023
+ CapacityReservation
3024
+ Information about the Capacity Reservation used by an instance or instance group.
3025
+
3026
+ Attributes
3027
+ ----------------------
3028
+ arn: The Amazon Resource Name (ARN) of the Capacity Reservation.
3029
+ type: The type of Capacity Reservation. Valid values are ODCR (On-Demand Capacity Reservation) or CRG (Capacity Reservation Group).
3030
+ """
3031
+
3032
+ arn: Optional[str] = Unassigned()
3033
+ type: Optional[str] = Unassigned()
3034
+
3035
+
2904
3036
  class CapacitySizeConfig(Base):
2905
3037
  """
2906
3038
  CapacitySizeConfig
@@ -3287,6 +3419,174 @@ class ClusterEbsVolumeConfig(Base):
3287
3419
  volume_size_in_gb: Optional[int] = Unassigned()
3288
3420
 
3289
3421
 
3422
+ class ClusterMetadata(Base):
3423
+ """
3424
+ ClusterMetadata
3425
+ Metadata information about a HyperPod cluster showing information about the cluster level operations, such as creating, updating, and deleting.
3426
+
3427
+ Attributes
3428
+ ----------------------
3429
+ failure_message: An error message describing why the cluster level operation (such as creating, updating, or deleting) failed.
3430
+ eks_role_access_entries: A list of Amazon EKS IAM role ARNs associated with the cluster. This is created by HyperPod on your behalf and only applies for EKS orchestrated clusters.
3431
+ slr_access_entry: The Service-Linked Role (SLR) associated with the cluster. This is created by HyperPod on your behalf and only applies for EKS orchestrated clusters.
3432
+ """
3433
+
3434
+ failure_message: Optional[str] = Unassigned()
3435
+ eks_role_access_entries: Optional[List[str]] = Unassigned()
3436
+ slr_access_entry: Optional[str] = Unassigned()
3437
+
3438
+
3439
+ class InstanceGroupMetadata(Base):
3440
+ """
3441
+ InstanceGroupMetadata
3442
+ Metadata information about an instance group in a HyperPod cluster.
3443
+
3444
+ Attributes
3445
+ ----------------------
3446
+ failure_message: An error message describing why the instance group level operation (such as creating, scaling, or deleting) failed.
3447
+ availability_zone_id: The ID of the Availability Zone where the instance group is located.
3448
+ capacity_reservation: Information about the Capacity Reservation used by the instance group.
3449
+ subnet_id: The ID of the subnet where the instance group is located.
3450
+ security_group_ids: A list of security group IDs associated with the instance group.
3451
+ ami_override: If you use a custom Amazon Machine Image (AMI) for the instance group, this field shows the ID of the custom AMI.
3452
+ """
3453
+
3454
+ failure_message: Optional[str] = Unassigned()
3455
+ availability_zone_id: Optional[str] = Unassigned()
3456
+ capacity_reservation: Optional[CapacityReservation] = Unassigned()
3457
+ subnet_id: Optional[str] = Unassigned()
3458
+ security_group_ids: Optional[List[str]] = Unassigned()
3459
+ ami_override: Optional[str] = Unassigned()
3460
+
3461
+
3462
+ class InstanceGroupScalingMetadata(Base):
3463
+ """
3464
+ InstanceGroupScalingMetadata
3465
+ Metadata information about scaling operations for an instance group.
3466
+
3467
+ Attributes
3468
+ ----------------------
3469
+ instance_count: The current number of instances in the group.
3470
+ target_count: The desired number of instances for the group after scaling.
3471
+ failure_message: An error message describing why the scaling operation failed, if applicable.
3472
+ """
3473
+
3474
+ instance_count: Optional[int] = Unassigned()
3475
+ target_count: Optional[int] = Unassigned()
3476
+ failure_message: Optional[str] = Unassigned()
3477
+
3478
+
3479
+ class InstanceMetadata(Base):
3480
+ """
3481
+ InstanceMetadata
3482
+ Metadata information about an instance in a HyperPod cluster.
3483
+
3484
+ Attributes
3485
+ ----------------------
3486
+ customer_eni: The ID of the customer-managed Elastic Network Interface (ENI) associated with the instance.
3487
+ additional_enis: Information about additional Elastic Network Interfaces (ENIs) associated with the instance.
3488
+ capacity_reservation: Information about the Capacity Reservation used by the instance.
3489
+ failure_message: An error message describing why the instance creation or update failed, if applicable.
3490
+ lcs_execution_state: The execution state of the Lifecycle Script (LCS) for the instance.
3491
+ node_logical_id: The unique logical identifier of the node within the cluster. The ID used here is the same object as in the BatchAddClusterNodes API.
3492
+ """
3493
+
3494
+ customer_eni: Optional[str] = Unassigned()
3495
+ additional_enis: Optional[AdditionalEnis] = Unassigned()
3496
+ capacity_reservation: Optional[CapacityReservation] = Unassigned()
3497
+ failure_message: Optional[str] = Unassigned()
3498
+ lcs_execution_state: Optional[str] = Unassigned()
3499
+ node_logical_id: Optional[str] = Unassigned()
3500
+
3501
+
3502
+ class EventMetadata(Base):
3503
+ """
3504
+ EventMetadata
3505
+ Metadata associated with a cluster event, which may include details about various resource types.
3506
+
3507
+ Attributes
3508
+ ----------------------
3509
+ cluster: Metadata specific to cluster-level events.
3510
+ instance_group: Metadata specific to instance group-level events.
3511
+ instance_group_scaling: Metadata related to instance group scaling events.
3512
+ instance: Metadata specific to instance-level events.
3513
+ """
3514
+
3515
+ cluster: Optional[ClusterMetadata] = Unassigned()
3516
+ instance_group: Optional[InstanceGroupMetadata] = Unassigned()
3517
+ instance_group_scaling: Optional[InstanceGroupScalingMetadata] = Unassigned()
3518
+ instance: Optional[InstanceMetadata] = Unassigned()
3519
+
3520
+
3521
+ class EventDetails(Base):
3522
+ """
3523
+ EventDetails
3524
+ Detailed information about a specific event, including event metadata.
3525
+
3526
+ Attributes
3527
+ ----------------------
3528
+ event_metadata: Metadata specific to the event, which may include information about the cluster, instance group, or instance involved.
3529
+ """
3530
+
3531
+ event_metadata: Optional[EventMetadata] = Unassigned()
3532
+
3533
+
3534
+ class ClusterEventDetail(Base):
3535
+ """
3536
+ ClusterEventDetail
3537
+ Detailed information about a specific event in a HyperPod cluster.
3538
+
3539
+ Attributes
3540
+ ----------------------
3541
+ event_id: The unique identifier (UUID) of the event.
3542
+ cluster_arn: The Amazon Resource Name (ARN) of the HyperPod cluster associated with the event.
3543
+ cluster_name: The name of the HyperPod cluster associated with the event.
3544
+ instance_group_name: The name of the instance group associated with the event, if applicable.
3545
+ instance_id: The EC2 instance ID associated with the event, if applicable.
3546
+ resource_type: The type of resource associated with the event. Valid values are Cluster, InstanceGroup, or Instance.
3547
+ event_time: The timestamp when the event occurred.
3548
+ event_details: Additional details about the event, including event-specific metadata.
3549
+ description: A human-readable description of the event.
3550
+ """
3551
+
3552
+ event_id: str
3553
+ cluster_arn: str
3554
+ cluster_name: Union[str, object]
3555
+ resource_type: str
3556
+ event_time: datetime.datetime
3557
+ instance_group_name: Optional[str] = Unassigned()
3558
+ instance_id: Optional[str] = Unassigned()
3559
+ event_details: Optional[EventDetails] = Unassigned()
3560
+ description: Optional[str] = Unassigned()
3561
+
3562
+
3563
+ class ClusterEventSummary(Base):
3564
+ """
3565
+ ClusterEventSummary
3566
+ A summary of an event in a HyperPod cluster.
3567
+
3568
+ Attributes
3569
+ ----------------------
3570
+ event_id: The unique identifier (UUID) of the event.
3571
+ cluster_arn: The Amazon Resource Name (ARN) of the HyperPod cluster associated with the event.
3572
+ cluster_name: The name of the HyperPod cluster associated with the event.
3573
+ instance_group_name: The name of the instance group associated with the event, if applicable.
3574
+ instance_id: The Amazon Elastic Compute Cloud (EC2) instance ID associated with the event, if applicable.
3575
+ resource_type: The type of resource associated with the event. Valid values are Cluster, InstanceGroup, or Instance.
3576
+ event_time: The timestamp when the event occurred.
3577
+ description: A brief, human-readable description of the event.
3578
+ """
3579
+
3580
+ event_id: str
3581
+ cluster_arn: str
3582
+ cluster_name: Union[str, object]
3583
+ resource_type: str
3584
+ event_time: datetime.datetime
3585
+ instance_group_name: Optional[str] = Unassigned()
3586
+ instance_id: Optional[str] = Unassigned()
3587
+ description: Optional[str] = Unassigned()
3588
+
3589
+
3290
3590
  class ClusterLifeCycleConfig(Base):
3291
3591
  """
3292
3592
  ClusterLifeCycleConfig
@@ -3383,6 +3683,8 @@ class ClusterInstanceGroupDetails(Base):
3383
3683
  training_plan_status: The current status of the training plan associated with this cluster instance group.
3384
3684
  override_vpc_config: The customized Amazon VPC configuration at the instance group level that overrides the default Amazon VPC configuration of the SageMaker HyperPod cluster.
3385
3685
  scheduled_update_config: The configuration object of the schedule that SageMaker follows when updating the AMI.
3686
+ current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the instance group.
3687
+ desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the instance group.
3386
3688
  """
3387
3689
 
3388
3690
  current_count: Optional[int] = Unassigned()
@@ -3399,6 +3701,8 @@ class ClusterInstanceGroupDetails(Base):
3399
3701
  training_plan_status: Optional[str] = Unassigned()
3400
3702
  override_vpc_config: Optional[VpcConfig] = Unassigned()
3401
3703
  scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned()
3704
+ current_image_id: Optional[str] = Unassigned()
3705
+ desired_image_id: Optional[str] = Unassigned()
3402
3706
 
3403
3707
 
3404
3708
  class ClusterInstanceGroupSpecification(Base):
@@ -3419,6 +3723,7 @@ class ClusterInstanceGroupSpecification(Base):
3419
3723
  training_plan_arn: The Amazon Resource Name (ARN); of the training plan to use for this cluster instance group. For more information about how to reserve GPU capacity for your SageMaker HyperPod clusters using Amazon SageMaker Training Plan, see CreateTrainingPlan .
3420
3724
  override_vpc_config: To configure multi-AZ deployments, customize the Amazon VPC configuration at the instance group level. You can specify different subnets and security groups across different AZs in the instance group specification to override a SageMaker HyperPod cluster's default Amazon VPC configuration. For more information about deploying a cluster in multiple AZs, see Setting up SageMaker HyperPod clusters across multiple AZs. When your Amazon VPC and subnets support IPv6, network communications differ based on the cluster orchestration platform: Slurm-orchestrated clusters automatically configure nodes with dual IPv6 and IPv4 addresses, allowing immediate IPv6 network communications. 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 Amazon EKS IPv6 Cluster Deployment. Additional resources for IPv6 configuration: For information about adding IPv6 support to your VPC, see to IPv6 Support for VPC. For information about creating a new IPv6-compatible VPC, see Amazon VPC Creation Guide. To configure SageMaker HyperPod with a custom Amazon VPC, see Custom Amazon VPC Setup for SageMaker HyperPod.
3421
3725
  scheduled_update_config: The configuration object of the schedule that SageMaker uses to update the AMI.
3726
+ image_id: When configuring your HyperPod cluster, you can specify an image ID using one of the following options: HyperPodPublicAmiId: Use a HyperPod public AMI CustomAmiId: Use your custom AMI default: Use the default latest system image f you choose to use a custom AMI (CustomAmiId), ensure it meets the following requirements: Encryption: The custom AMI must be unencrypted. Ownership: The custom AMI must be owned by the same Amazon Web Services account that is creating the HyperPod cluster. Volume support: Only the primary AMI snapshot volume is supported; additional AMI volumes are not supported. When updating the instance group's AMI through the UpdateClusterSoftware operation, if an instance group uses a custom AMI, you must provide an ImageId or use the default as input.
3422
3727
  """
3423
3728
 
3424
3729
  instance_count: int
@@ -3432,6 +3737,7 @@ class ClusterInstanceGroupSpecification(Base):
3432
3737
  training_plan_arn: Optional[str] = Unassigned()
3433
3738
  override_vpc_config: Optional[VpcConfig] = Unassigned()
3434
3739
  scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned()
3740
+ image_id: Optional[str] = Unassigned()
3435
3741
 
3436
3742
 
3437
3743
  class ClusterInstancePlacement(Base):
@@ -3464,6 +3770,19 @@ class ClusterInstanceStatusDetails(Base):
3464
3770
  message: Optional[str] = Unassigned()
3465
3771
 
3466
3772
 
3773
+ class UltraServerInfo(Base):
3774
+ """
3775
+ UltraServerInfo
3776
+ Contains information about the UltraServer object.
3777
+
3778
+ Attributes
3779
+ ----------------------
3780
+ id: The unique identifier of the UltraServer.
3781
+ """
3782
+
3783
+ id: Optional[str] = Unassigned()
3784
+
3785
+
3467
3786
  class ClusterNodeDetails(Base):
3468
3787
  """
3469
3788
  ClusterNodeDetails
@@ -3473,6 +3792,7 @@ class ClusterNodeDetails(Base):
3473
3792
  ----------------------
3474
3793
  instance_group_name: The instance group name in which the instance is.
3475
3794
  instance_id: The ID of the instance.
3795
+ node_logical_id: A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId.
3476
3796
  instance_status: The status of the instance.
3477
3797
  instance_type: The type of the instance.
3478
3798
  launch_time: The time when the instance is launched.
@@ -3485,10 +3805,14 @@ class ClusterNodeDetails(Base):
3485
3805
  private_primary_ipv6: The private primary IPv6 address of the SageMaker HyperPod cluster node when configured with an Amazon VPC that supports IPv6 and includes subnets with IPv6 addressing enabled in either the cluster Amazon VPC configuration or the instance group Amazon VPC configuration.
3486
3806
  private_dns_hostname: The private DNS hostname of the SageMaker HyperPod cluster node.
3487
3807
  placement: The placement details of the SageMaker HyperPod cluster node.
3808
+ current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the node.
3809
+ desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the node.
3810
+ ultra_server_info: Contains information about the UltraServer.
3488
3811
  """
3489
3812
 
3490
3813
  instance_group_name: Optional[str] = Unassigned()
3491
3814
  instance_id: Optional[str] = Unassigned()
3815
+ node_logical_id: Optional[str] = Unassigned()
3492
3816
  instance_status: Optional[ClusterInstanceStatusDetails] = Unassigned()
3493
3817
  instance_type: Optional[str] = Unassigned()
3494
3818
  launch_time: Optional[datetime.datetime] = Unassigned()
@@ -3501,6 +3825,9 @@ class ClusterNodeDetails(Base):
3501
3825
  private_primary_ipv6: Optional[str] = Unassigned()
3502
3826
  private_dns_hostname: Optional[str] = Unassigned()
3503
3827
  placement: Optional[ClusterInstancePlacement] = Unassigned()
3828
+ current_image_id: Optional[str] = Unassigned()
3829
+ desired_image_id: Optional[str] = Unassigned()
3830
+ ultra_server_info: Optional[UltraServerInfo] = Unassigned()
3504
3831
 
3505
3832
 
3506
3833
  class ClusterNodeSummary(Base):
@@ -3512,10 +3839,12 @@ class ClusterNodeSummary(Base):
3512
3839
  ----------------------
3513
3840
  instance_group_name: The name of the instance group in which the instance is.
3514
3841
  instance_id: The ID of the instance.
3842
+ node_logical_id: A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId. This field is only included when IncludeNodeLogicalIds is set to True in the ListClusterNodes request.
3515
3843
  instance_type: The type of the instance.
3516
3844
  launch_time: The time when the instance is launched.
3517
3845
  last_software_update_time: The time when SageMaker last updated the software of the instances in the cluster.
3518
3846
  instance_status: The status of the instance.
3847
+ ultra_server_info: Contains information about the UltraServer.
3519
3848
  """
3520
3849
 
3521
3850
  instance_group_name: str
@@ -3523,7 +3852,9 @@ class ClusterNodeSummary(Base):
3523
3852
  instance_type: str
3524
3853
  launch_time: datetime.datetime
3525
3854
  instance_status: ClusterInstanceStatusDetails
3855
+ node_logical_id: Optional[str] = Unassigned()
3526
3856
  last_software_update_time: Optional[datetime.datetime] = Unassigned()
3857
+ ultra_server_info: Optional[UltraServerInfo] = Unassigned()
3527
3858
 
3528
3859
 
3529
3860
  class ClusterOrchestratorEksConfig(Base):
@@ -9356,6 +9687,27 @@ class TemplateProviderDetail(Base):
9356
9687
  cfn_template_provider_detail: Optional[CfnTemplateProviderDetail] = Unassigned()
9357
9688
 
9358
9689
 
9690
+ class UltraServerSummary(Base):
9691
+ """
9692
+ UltraServerSummary
9693
+ A summary of UltraServer resources and their current status.
9694
+
9695
+ Attributes
9696
+ ----------------------
9697
+ ultra_server_type: The type of UltraServer, such as ml.u-p6e-gb200x72.
9698
+ instance_type: The Amazon EC2 instance type used in the UltraServer.
9699
+ ultra_server_count: The number of UltraServers of this type.
9700
+ available_spare_instance_count: The number of available spare instances in the UltraServers.
9701
+ unhealthy_instance_count: The total number of instances across all UltraServers of this type that are currently in an unhealthy state.
9702
+ """
9703
+
9704
+ ultra_server_type: str
9705
+ instance_type: str
9706
+ ultra_server_count: Optional[int] = Unassigned()
9707
+ available_spare_instance_count: Optional[int] = Unassigned()
9708
+ unhealthy_instance_count: Optional[int] = Unassigned()
9709
+
9710
+
9359
9711
  class SubscribedWorkteam(Base):
9360
9712
  """
9361
9713
  SubscribedWorkteam
@@ -9459,6 +9811,9 @@ class ReservedCapacitySummary(Base):
9459
9811
  Attributes
9460
9812
  ----------------------
9461
9813
  reserved_capacity_arn: The Amazon Resource Name (ARN); of the reserved capacity.
9814
+ reserved_capacity_type: The type of reserved capacity.
9815
+ ultra_server_type: The type of UltraServer included in this reserved capacity, such as ml.u-p6e-gb200x72.
9816
+ ultra_server_count: The number of UltraServers included in this reserved capacity.
9462
9817
  instance_type: The instance type for the reserved capacity.
9463
9818
  total_instance_count: The total number of instances in the reserved capacity.
9464
9819
  status: The current status of the reserved capacity.
@@ -9473,6 +9828,9 @@ class ReservedCapacitySummary(Base):
9473
9828
  instance_type: str
9474
9829
  total_instance_count: int
9475
9830
  status: str
9831
+ reserved_capacity_type: Optional[str] = Unassigned()
9832
+ ultra_server_type: Optional[str] = Unassigned()
9833
+ ultra_server_count: Optional[int] = Unassigned()
9476
9834
  availability_zone: Optional[str] = Unassigned()
9477
9835
  duration_hours: Optional[int] = Unassigned()
9478
9836
  duration_minutes: Optional[int] = Unassigned()
@@ -11925,6 +12283,7 @@ class TrainingPlanSummary(Base):
11925
12283
  total_instance_count: The total number of instances reserved in this training plan.
11926
12284
  available_instance_count: The number of instances currently available for use in this training plan.
11927
12285
  in_use_instance_count: The number of instances currently in use from this training plan.
12286
+ total_ultra_server_count: The total number of UltraServers allocated to this training plan.
11928
12287
  target_resources: The target resources (e.g., training jobs, HyperPod clusters) that can use this training plan. Training plans are specific to their target resource. A training plan designed for SageMaker training jobs can only be used to schedule and run training jobs. A training plan for HyperPod clusters can be used exclusively to provide compute resources to a cluster's instance group.
11929
12288
  reserved_capacity_summaries: A list of reserved capacities associated with this training plan, including details such as instance types, counts, and availability zones.
11930
12289
  """
@@ -11942,6 +12301,7 @@ class TrainingPlanSummary(Base):
11942
12301
  total_instance_count: Optional[int] = Unassigned()
11943
12302
  available_instance_count: Optional[int] = Unassigned()
11944
12303
  in_use_instance_count: Optional[int] = Unassigned()
12304
+ total_ultra_server_count: Optional[int] = Unassigned()
11945
12305
  target_resources: Optional[List[str]] = Unassigned()
11946
12306
  reserved_capacity_summaries: Optional[List[ReservedCapacitySummary]] = Unassigned()
11947
12307
 
@@ -12027,6 +12387,39 @@ class TrialSummary(Base):
12027
12387
  last_modified_time: Optional[datetime.datetime] = Unassigned()
12028
12388
 
12029
12389
 
12390
+ class UltraServer(Base):
12391
+ """
12392
+ UltraServer
12393
+ Represents a high-performance compute server used for distributed training in SageMaker AI. An UltraServer consists of multiple instances within a shared NVLink interconnect domain.
12394
+
12395
+ Attributes
12396
+ ----------------------
12397
+ ultra_server_id: The unique identifier for the UltraServer.
12398
+ ultra_server_type: The type of UltraServer, such as ml.u-p6e-gb200x72.
12399
+ availability_zone: The name of the Availability Zone where the UltraServer is provisioned.
12400
+ instance_type: The Amazon EC2 instance type used in the UltraServer.
12401
+ total_instance_count: The total number of instances in this UltraServer.
12402
+ configured_spare_instance_count: The number of spare instances configured for this UltraServer to provide enhanced resiliency.
12403
+ available_instance_count: The number of instances currently available for use in this UltraServer.
12404
+ in_use_instance_count: The number of instances currently in use in this UltraServer.
12405
+ available_spare_instance_count: The number of available spare instances in the UltraServer.
12406
+ unhealthy_instance_count: The number of instances in this UltraServer that are currently in an unhealthy state.
12407
+ health_status: The overall health status of the UltraServer.
12408
+ """
12409
+
12410
+ ultra_server_id: str
12411
+ ultra_server_type: str
12412
+ availability_zone: str
12413
+ instance_type: str
12414
+ total_instance_count: int
12415
+ configured_spare_instance_count: Optional[int] = Unassigned()
12416
+ available_instance_count: Optional[int] = Unassigned()
12417
+ in_use_instance_count: Optional[int] = Unassigned()
12418
+ available_spare_instance_count: Optional[int] = Unassigned()
12419
+ unhealthy_instance_count: Optional[int] = Unassigned()
12420
+ health_status: Optional[str] = Unassigned()
12421
+
12422
+
12030
12423
  class UserProfileDetails(Base):
12031
12424
  """
12032
12425
  UserProfileDetails
@@ -12746,6 +13139,9 @@ class ReservedCapacityOffering(Base):
12746
13139
 
12747
13140
  Attributes
12748
13141
  ----------------------
13142
+ reserved_capacity_type: The type of reserved capacity offering.
13143
+ ultra_server_type: The type of UltraServer included in this reserved capacity offering, such as ml.u-p6e-gb200x72.
13144
+ ultra_server_count: The number of UltraServers included in this reserved capacity offering.
12749
13145
  instance_type: The instance type for the reserved capacity offering.
12750
13146
  instance_count: The number of instances in the reserved capacity offering.
12751
13147
  availability_zone: The availability zone for the reserved capacity offering.
@@ -12757,6 +13153,9 @@ class ReservedCapacityOffering(Base):
12757
13153
 
12758
13154
  instance_type: str
12759
13155
  instance_count: int
13156
+ reserved_capacity_type: Optional[str] = Unassigned()
13157
+ ultra_server_type: Optional[str] = Unassigned()
13158
+ ultra_server_count: Optional[int] = Unassigned()
12760
13159
  availability_zone: Optional[str] = Unassigned()
12761
13160
  duration_hours: Optional[int] = Unassigned()
12762
13161
  duration_minutes: Optional[int] = Unassigned()
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: sagemaker-core
3
- Version: 1.0.48
3
+ Version: 1.0.50
4
4
  Summary: An python package for sagemaker core functionalities
5
5
  Author-email: AWS <sagemaker-interests@amazon.com>
6
6
  Project-URL: Repository, https://github.com/aws/sagemaker-core.git
@@ -7,15 +7,15 @@ sagemaker_core/main/config_schema.py,sha256=Wxe2gJash1rrxBomGhSYmII1LmJ3E70LIuSW
7
7
  sagemaker_core/main/default_configs_helper.py,sha256=bg_tgczX_bYzNiSlalJ6TWPTgrQYsI0uZguP5TIbPiw,8324
8
8
  sagemaker_core/main/exceptions.py,sha256=CsiM3V_Gb16grBotnu59LB6tznryPcSvAQDAOOYGc10,5563
9
9
  sagemaker_core/main/logs.py,sha256=yfEH7uP91nbE1lefymOlBr81ziBzsDSIOF2Qyd54FJE,6241
10
- sagemaker_core/main/resources.py,sha256=lDuKu3EHRhEjOE6MVLHfPABxGzBNHh8R2j961ITdMA0,1437580
11
- sagemaker_core/main/shapes.py,sha256=sGjB8ICd0F5bYmvFx1Y1yvscFS00sg6RCjrMR3CXx9s,762943
10
+ sagemaker_core/main/resources.py,sha256=kEaZjAloY9vmhsHU88kIWfNgM6RPYPkcWRBScLdaUdE,1441209
11
+ sagemaker_core/main/shapes.py,sha256=wy8DWtBaxC0_NcfCA1Yh-xWRAyZu_M5dqjAKomkhzk0,781903
12
12
  sagemaker_core/main/user_agent.py,sha256=BPYDAfDd70ObP-VAjl7aDHALHyGknkpRP21ktVr_LDw,2744
13
13
  sagemaker_core/main/utils.py,sha256=y1aZzztCApczZSqT0U7_H8zLlpqp1vgoUKcp40mTM2o,19157
14
14
  sagemaker_core/main/code_injection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
15
15
  sagemaker_core/main/code_injection/base.py,sha256=11_Jif0nOzfbLGlXaacKf-wcizzfS64U0OSZGoVffFU,1733
16
16
  sagemaker_core/main/code_injection/codec.py,sha256=2YzJ-iYEzmguVaJVcZeyCR0OpTSR7UOixATrOm4MiBk,8885
17
17
  sagemaker_core/main/code_injection/constants.py,sha256=2ICExGge8vAWx7lSTW0JGh-bH1korkvpOpDu5M63eI4,980
18
- sagemaker_core/main/code_injection/shape_dag.py,sha256=m19s6YykKJgkM5mX4t_aCoMlmZVpXR2h6nwy_mYVM5Q,726467
18
+ sagemaker_core/main/code_injection/shape_dag.py,sha256=lzvu_kntQlWCTPHhqqiFC6060b5yMxz2V30ZhbMJ2no,744763
19
19
  sagemaker_core/resources/__init__.py,sha256=EAYTFMN-nPjnPjjBbhIUeaL67FLKNPd7qbcbl9VIrws,31
20
20
  sagemaker_core/shapes/__init__.py,sha256=RnbIu9eTxKt-DNsOFJabrWIgrrtS9_SdAozP9JBl_ic,28
21
21
  sagemaker_core/tools/__init__.py,sha256=xX79JImxCVzrWMnjgntLCve2G5I-R4pRar5s20kT9Rs,56
@@ -28,8 +28,8 @@ sagemaker_core/tools/resources_extractor.py,sha256=hN61ehZbPnhFW-2FIVDi7NsEz4rLv
28
28
  sagemaker_core/tools/shapes_codegen.py,sha256=4lsePZpjk7M6RpJs5yar_m4z5MzwGHFrvCkdS_-R12c,12172
29
29
  sagemaker_core/tools/shapes_extractor.py,sha256=vxVKjXD3lmjrkoKiexjUnOt8ITbFxQSeiDtx7P6Qtkw,14226
30
30
  sagemaker_core/tools/templates.py,sha256=0lOIH3Rq2CXWkQhK6VenN_TE_v5p852s2kQyb_BeQxA,23460
31
- sagemaker_core-1.0.48.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
32
- sagemaker_core-1.0.48.dist-info/METADATA,sha256=enC8HCSHEqfxtM05NfKFnWazNYuv49H95De1E4mMKTY,4871
33
- sagemaker_core-1.0.48.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
34
- sagemaker_core-1.0.48.dist-info/top_level.txt,sha256=R3GAZZ1zC5JxqdE_0x2Lu_WYi2Xfke7VsiP3L5zngfA,15
35
- sagemaker_core-1.0.48.dist-info/RECORD,,
31
+ sagemaker_core-1.0.50.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
32
+ sagemaker_core-1.0.50.dist-info/METADATA,sha256=Y2sH1IHQP_7E-zDA4Q_8xsvEdBvBV-_bnBvxtegXemo,4871
33
+ sagemaker_core-1.0.50.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
34
+ sagemaker_core-1.0.50.dist-info/top_level.txt,sha256=R3GAZZ1zC5JxqdE_0x2Lu_WYi2Xfke7VsiP3L5zngfA,15
35
+ sagemaker_core-1.0.50.dist-info/RECORD,,