sagemaker-core 1.0.49__tar.gz → 1.0.51__tar.gz

{sagemaker_core-1.0.49/src/sagemaker_core.egg-info → sagemaker_core-1.0.51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sagemaker-core
-Version: 1.0.49
+Version: 1.0.51
 Summary: An python package for sagemaker core functionalities
 Author-email: AWS <sagemaker-interests@amazon.com>
 Project-URL: Repository, https://github.com/aws/sagemaker-core.git

sagemaker_core-1.0.51/VERSION

@@ -0,0 +1 @@
+1.0.51

{sagemaker_core-1.0.49 → sagemaker_core-1.0.51}/src/sagemaker_core/main/code_injection/shape_dag.py

@@ -1623,6 +1623,7 @@ SHAPE_DAG = {
             {"name": "Placement", "shape": "ClusterInstancePlacement", "type": "structure"},
             {"name": "CurrentImageId", "shape": "ImageId", "type": "string"},
             {"name": "DesiredImageId", "shape": "ImageId", "type": "string"},
+            {"name": "UltraServerInfo", "shape": "UltraServerInfo", "type": "structure"},
         ],
         "type": "structure",
     },
@@ -1650,6 +1651,7 @@ SHAPE_DAG = {
                 "shape": "ClusterInstanceStatusDetails",
                 "type": "structure",
             },
+            {"name": "UltraServerInfo", "shape": "UltraServerInfo", "type": "structure"},
         ],
         "type": "structure",
     },
@@ -3438,6 +3440,11 @@ SHAPE_DAG = {
         "members": [
             {"name": "TrainingPlanName", "shape": "TrainingPlanName", "type": "string"},
             {"name": "TrainingPlanOfferingId", "shape": "TrainingPlanOfferingId", "type": "string"},
+            {
+                "name": "SpareInstanceCountPerUltraServer",
+                "shape": "SpareInstanceCountPerUltraServer",
+                "type": "integer",
+            },
             {"name": "Tags", "shape": "TagList", "type": "list"},
         ],
         "type": "structure",
@@ -4450,6 +4457,11 @@ SHAPE_DAG = {
             {"name": "UserProfileName", "shape": "UserProfileName", "type": "string"},
             {"name": "SpaceName", "shape": "SpaceName", "type": "string"},
             {"name": "Status", "shape": "AppStatus", "type": "string"},
+            {
+                "name": "EffectiveTrustedIdentityPropagationStatus",
+                "shape": "FeatureStatus",
+                "type": "string",
+            },
             {"name": "RecoveryMode", "shape": "Boolean", "type": "boolean"},
             {"name": "LastHealthCheckTimestamp", "shape": "Timestamp", "type": "timestamp"},
             {"name": "LastUserActivityTimestamp", "shape": "Timestamp", "type": "timestamp"},
@@ -6112,6 +6124,34 @@ SHAPE_DAG = {
         ],
         "type": "structure",
     },
+    "DescribeReservedCapacityRequest": {
+        "members": [
+            {"name": "ReservedCapacityArn", "shape": "ReservedCapacityArn", "type": "string"}
+        ],
+        "type": "structure",
+    },
+    "DescribeReservedCapacityResponse": {
+        "members": [
+            {"name": "ReservedCapacityArn", "shape": "ReservedCapacityArn", "type": "string"},
+            {"name": "ReservedCapacityType", "shape": "ReservedCapacityType", "type": "string"},
+            {"name": "Status", "shape": "ReservedCapacityStatus", "type": "string"},
+            {"name": "AvailabilityZone", "shape": "AvailabilityZone", "type": "string"},
+            {"name": "DurationHours", "shape": "ReservedCapacityDurationHours", "type": "long"},
+            {"name": "DurationMinutes", "shape": "ReservedCapacityDurationMinutes", "type": "long"},
+            {"name": "StartTime", "shape": "Timestamp", "type": "timestamp"},
+            {"name": "EndTime", "shape": "Timestamp", "type": "timestamp"},
+            {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
+            {"name": "TotalInstanceCount", "shape": "TotalInstanceCount", "type": "integer"},
+            {
+                "name": "AvailableInstanceCount",
+                "shape": "AvailableInstanceCount",
+                "type": "integer",
+            },
+            {"name": "InUseInstanceCount", "shape": "InUseInstanceCount", "type": "integer"},
+            {"name": "UltraServerSummary", "shape": "UltraServerSummary", "type": "structure"},
+        ],
+        "type": "structure",
+    },
     "DescribeSpaceRequest": {
         "members": [
             {"name": "DomainId", "shape": "DomainId", "type": "string"},
@@ -6287,6 +6327,17 @@ SHAPE_DAG = {
                 "type": "integer",
             },
             {"name": "InUseInstanceCount", "shape": "InUseInstanceCount", "type": "integer"},
+            {
+                "name": "UnhealthyInstanceCount",
+                "shape": "UnhealthyInstanceCount",
+                "type": "integer",
+            },
+            {
+                "name": "AvailableSpareInstanceCount",
+                "shape": "AvailableSpareInstanceCount",
+                "type": "integer",
+            },
+            {"name": "TotalUltraServerCount", "shape": "UltraServerCount", "type": "integer"},
             {"name": "TargetResources", "shape": "SageMakerResourceNames", "type": "list"},
             {
                 "name": "ReservedCapacitySummaries",
@@ -6596,6 +6647,11 @@ SHAPE_DAG = {
                 "shape": "ExecutionRoleIdentityConfig",
                 "type": "string",
             },
+            {
+                "name": "TrustedIdentityPropagationSettings",
+                "shape": "TrustedIdentityPropagationSettings",
+                "type": "structure",
+            },
             {"name": "DockerSettings", "shape": "DockerSettings", "type": "structure"},
             {"name": "AmazonQSettings", "shape": "AmazonQSettings", "type": "structure"},
             {
@@ -6619,6 +6675,11 @@ SHAPE_DAG = {
                 "type": "string",
             },
             {"name": "SecurityGroupIds", "shape": "DomainSecurityGroupIds", "type": "list"},
+            {
+                "name": "TrustedIdentityPropagationSettings",
+                "shape": "TrustedIdentityPropagationSettings",
+                "type": "structure",
+            },
             {"name": "DockerSettings", "shape": "DockerSettings", "type": "structure"},
             {"name": "AmazonQSettings", "shape": "AmazonQSettings", "type": "structure"},
             {
@@ -8589,6 +8650,13 @@ SHAPE_DAG = {
         ],
         "type": "structure",
     },
+    "InstancePlacementConfig": {
+        "members": [
+            {"name": "EnableMultipleJobs", "shape": "Boolean", "type": "boolean"},
+            {"name": "PlacementSpecifications", "shape": "PlacementSpecifications", "type": "list"},
+        ],
+        "type": "structure",
+    },
     "IntegerParameterRange": {
         "members": [
             {"name": "Name", "shape": "ParameterKey", "type": "string"},
@@ -10756,6 +10824,21 @@ SHAPE_DAG = {
         ],
         "type": "structure",
     },
+    "ListUltraServersByReservedCapacityRequest": {
+        "members": [
+            {"name": "ReservedCapacityArn", "shape": "ReservedCapacityArn", "type": "string"},
+            {"name": "MaxResults", "shape": "MaxResults", "type": "integer"},
+            {"name": "NextToken", "shape": "NextToken", "type": "string"},
+        ],
+        "type": "structure",
+    },
+    "ListUltraServersByReservedCapacityResponse": {
+        "members": [
+            {"name": "NextToken", "shape": "NextToken", "type": "string"},
+            {"name": "UltraServers", "shape": "UltraServers", "type": "list"},
+        ],
+        "type": "structure",
+    },
     "ListUserProfilesRequest": {
         "members": [
             {"name": "NextToken", "shape": "NextToken", "type": "string"},
@@ -12800,6 +12883,18 @@ SHAPE_DAG = {
         "member_type": "structure",
         "type": "list",
     },
+    "PlacementSpecification": {
+        "members": [
+            {"name": "UltraServerId", "shape": "String256", "type": "string"},
+            {"name": "InstanceCount", "shape": "TrainingInstanceCount", "type": "integer"},
+        ],
+        "type": "structure",
+    },
+    "PlacementSpecifications": {
+        "member_shape": "PlacementSpecification",
+        "member_type": "structure",
+        "type": "list",
+    },
     "PredefinedMetricSpecification": {
         "members": [{"name": "PredefinedMetricType", "shape": "String", "type": "string"}],
         "type": "structure",
@@ -13737,6 +13832,9 @@ SHAPE_DAG = {
     },
     "ReservedCapacityOffering": {
         "members": [
+            {"name": "ReservedCapacityType", "shape": "ReservedCapacityType", "type": "string"},
+            {"name": "UltraServerType", "shape": "UltraServerType", "type": "string"},
+            {"name": "UltraServerCount", "shape": "UltraServerCount", "type": "integer"},
             {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
             {"name": "InstanceCount", "shape": "ReservedCapacityInstanceCount", "type": "integer"},
             {"name": "AvailabilityZone", "shape": "AvailabilityZone", "type": "string"},
@@ -13760,6 +13858,9 @@ SHAPE_DAG = {
     "ReservedCapacitySummary": {
         "members": [
             {"name": "ReservedCapacityArn", "shape": "ReservedCapacityArn", "type": "string"},
+            {"name": "ReservedCapacityType", "shape": "ReservedCapacityType", "type": "string"},
+            {"name": "UltraServerType", "shape": "UltraServerType", "type": "string"},
+            {"name": "UltraServerCount", "shape": "UltraServerCount", "type": "integer"},
             {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
             {"name": "TotalInstanceCount", "shape": "TotalInstanceCount", "type": "integer"},
             {"name": "Status", "shape": "ReservedCapacityStatus", "type": "string"},
@@ -13810,6 +13911,11 @@ SHAPE_DAG = {
             },
             {"name": "InstanceGroups", "shape": "InstanceGroups", "type": "list"},
             {"name": "TrainingPlanArn", "shape": "TrainingPlanArn", "type": "string"},
+            {
+                "name": "InstancePlacementConfig",
+                "shape": "InstancePlacementConfig",
+                "type": "structure",
+            },
         ],
         "type": "structure",
     },
@@ -14132,6 +14238,8 @@ SHAPE_DAG = {
         "members": [
             {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
             {"name": "InstanceCount", "shape": "ReservedCapacityInstanceCount", "type": "integer"},
+            {"name": "UltraServerType", "shape": "UltraServerType", "type": "string"},
+            {"name": "UltraServerCount", "shape": "UltraServerCount", "type": "integer"},
             {"name": "StartTimeAfter", "shape": "Timestamp", "type": "timestamp"},
             {"name": "EndTimeBefore", "shape": "Timestamp", "type": "timestamp"},
             {"name": "DurationHours", "shape": "TrainingPlanDurationHoursInput", "type": "long"},
@@ -15153,6 +15261,7 @@ SHAPE_DAG = {
                 "type": "integer",
             },
             {"name": "InUseInstanceCount", "shape": "InUseInstanceCount", "type": "integer"},
+            {"name": "TotalUltraServerCount", "shape": "UltraServerCount", "type": "integer"},
             {"name": "TargetResources", "shape": "SageMakerResourceNames", "type": "list"},
             {
                 "name": "ReservedCapacitySummaries",
@@ -15499,6 +15608,10 @@ SHAPE_DAG = {
         ],
         "type": "structure",
     },
+    "TrustedIdentityPropagationSettings": {
+        "members": [{"name": "Status", "shape": "FeatureStatus", "type": "string"}],
+        "type": "structure",
+    },
     "TtlDuration": {
         "members": [
             {"name": "Unit", "shape": "TtlDurationUnit", "type": "string"},
@@ -15552,6 +15665,61 @@ SHAPE_DAG = {
         ],
         "type": "structure",
     },
+    "UltraServer": {
+        "members": [
+            {"name": "UltraServerId", "shape": "NonEmptyString256", "type": "string"},
+            {"name": "UltraServerType", "shape": "UltraServerType", "type": "string"},
+            {"name": "AvailabilityZone", "shape": "AvailabilityZone", "type": "string"},
+            {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
+            {"name": "TotalInstanceCount", "shape": "TotalInstanceCount", "type": "integer"},
+            {
+                "name": "ConfiguredSpareInstanceCount",
+                "shape": "ConfiguredSpareInstanceCount",
+                "type": "integer",
+            },
+            {
+                "name": "AvailableInstanceCount",
+                "shape": "AvailableInstanceCount",
+                "type": "integer",
+            },
+            {"name": "InUseInstanceCount", "shape": "InUseInstanceCount", "type": "integer"},
+            {
+                "name": "AvailableSpareInstanceCount",
+                "shape": "AvailableSpareInstanceCount",
+                "type": "integer",
+            },
+            {
+                "name": "UnhealthyInstanceCount",
+                "shape": "UnhealthyInstanceCount",
+                "type": "integer",
+            },
+            {"name": "HealthStatus", "shape": "UltraServerHealthStatus", "type": "string"},
+        ],
+        "type": "structure",
+    },
+    "UltraServerInfo": {
+        "members": [{"name": "Id", "shape": "String", "type": "string"}],
+        "type": "structure",
+    },
+    "UltraServerSummary": {
+        "members": [
+            {"name": "UltraServerType", "shape": "UltraServerType", "type": "string"},
+            {"name": "InstanceType", "shape": "ReservedCapacityInstanceType", "type": "string"},
+            {"name": "UltraServerCount", "shape": "UltraServerCount", "type": "integer"},
+            {
+                "name": "AvailableSpareInstanceCount",
+                "shape": "AvailableSpareInstanceCount",
+                "type": "integer",
+            },
+            {
+                "name": "UnhealthyInstanceCount",
+                "shape": "UnhealthyInstanceCount",
+                "type": "integer",
+            },
+        ],
+        "type": "structure",
+    },
+    "UltraServers": {"member_shape": "UltraServer", "member_type": "structure", "type": "list"},
     "UnifiedStudioSettings": {
         "members": [
             {"name": "StudioWebPortalAccess", "shape": "FeatureStatus", "type": "string"},

{sagemaker_core-1.0.49 → sagemaker_core-1.0.51}/src/sagemaker_core/main/resources.py

@@ -978,6 +978,7 @@ class App(Base):
         user_profile_name: The user profile name.
         space_name: The name of the space. If this value is not set, then UserProfileName must be set.
         status: The status.
+        effective_trusted_identity_propagation_status: The effective status of Trusted Identity Propagation (TIP) for this application. When enabled, user identities from IAM Identity Center are being propagated through the application to TIP enabled Amazon Web Services services. When disabled, standard IAM role-based access is used.
         recovery_mode:  Indicates whether the application is launched in recovery mode.
         last_health_check_timestamp: The timestamp of the last health check.
         last_user_activity_timestamp: The timestamp of the last user's activity. LastUserActivityTimestamp is also updated when SageMaker AI performs health checks without user activity. As a result, this value is set to the same value as LastHealthCheckTimestamp.
@@ -995,6 +996,7 @@ class App(Base):
     user_profile_name: Optional[str] = Unassigned()
     space_name: Optional[str] = Unassigned()
     status: Optional[str] = Unassigned()
+    effective_trusted_identity_propagation_status: Optional[str] = Unassigned()
     recovery_mode: Optional[bool] = Unassigned()
     last_health_check_timestamp: Optional[datetime.datetime] = Unassigned()
     last_user_activity_timestamp: Optional[datetime.datetime] = Unassigned()
@@ -3302,7 +3304,7 @@ class Cluster(Base):
             restricted_instance_groups: The specialized instance groups for training models like Amazon Nova to be created in the SageMaker HyperPod cluster.
             vpc_config: 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 Give SageMaker access to resources in your Amazon VPC.  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.
             tags: Custom tags for managing the SageMaker HyperPod cluster as an Amazon Web Services resource. You can add tags to your cluster in the same way you add them in other Amazon Web Services services that support tagging. To learn more about tagging Amazon Web Services resources in general, see Tagging Amazon Web Services Resources User Guide.
-            orchestrator: The type of orchestrator to use for the SageMaker HyperPod cluster. Currently, the only supported value is "eks", which is to use an Amazon Elastic Kubernetes Service (EKS) cluster as the orchestrator.
+            orchestrator: The type of orchestrator to use for the SageMaker HyperPod cluster. Currently, the only supported value is "eks", which is to use an Amazon Elastic Kubernetes Service cluster as the orchestrator.
             node_recovery: The node recovery mode for the SageMaker HyperPod cluster. When set to Automatic, SageMaker HyperPod will automatically reboot or replace faulty nodes when issues are detected. When set to None, cluster administrators will need to manually manage any faulty cluster instances.
             node_provisioning_mode: The mode for provisioning nodes in the cluster. You can specify the following modes:    Continuous: Scaling behavior that enables 1) concurrent operation execution within instance groups, 2) continuous retry mechanisms for failed operations, 3) enhanced customer visibility into cluster events through detailed event streams, 4) partial provisioning capabilities. Your clusters and instance groups remain InService while scaling. This mode is only supported for EKS orchestrated clusters.
             session: Boto3 session.
@@ -16933,7 +16935,7 @@ class LabelingJob(Base):
 
         Parameters:
             labeling_job_name: The name of the labeling job. This name is used to identify the job in a list of labeling jobs. Labeling job names must be unique within an Amazon Web Services account and region. LabelingJobName is not case sensitive. For example, Example-job and example-job are considered the same labeling job name by Ground Truth.
-            label_attribute_name: The attribute name to use for the label in the output manifest file. This is the key for the key/value pair formed with the label that a worker assigns to the object. The LabelAttributeName must meet the following requirements.   The name can't end with "-metadata".    If you are using one of the following built-in task types, the attribute name must end with "-ref". If the task type you are using is not listed below, the attribute name must not end with "-ref".   Image semantic segmentation (SemanticSegmentation), and adjustment (AdjustmentSemanticSegmentation) and verification (VerificationSemanticSegmentation) labeling jobs for this task type.   Video frame object detection (VideoObjectDetection), and adjustment and verification (AdjustmentVideoObjectDetection) labeling jobs for this task type.   Video frame object tracking (VideoObjectTracking), and adjustment and verification (AdjustmentVideoObjectTracking) labeling jobs for this task type.   3D point cloud semantic segmentation (3DPointCloudSemanticSegmentation), and adjustment and verification (Adjustment3DPointCloudSemanticSegmentation) labeling jobs for this task type.    3D point cloud object tracking (3DPointCloudObjectTracking), and adjustment and verification (Adjustment3DPointCloudObjectTracking) labeling jobs for this task type.        If you are creating an adjustment or verification labeling job, you must use a different LabelAttributeName than the one used in the original labeling job. The original labeling job is the Ground Truth labeling job that produced the labels that you want verified or adjusted. To learn more about adjustment and verification labeling jobs, see Verify and Adjust Labels.
+            label_attribute_name: The attribute name to use for the label in the output manifest file. This is the key for the key/value pair formed with the label that a worker assigns to the object. The LabelAttributeName must meet the following requirements.   The name can't end with "-metadata".    If you are using one of the following built-in task types, the attribute name must end with "-ref". If the task type you are using is not listed below, the attribute name must not end with "-ref".   Verification (VerificationSemanticSegmentation) labeling jobs for this task type.   Video frame object detection (VideoObjectDetection), and adjustment and verification (AdjustmentVideoObjectDetection) labeling jobs for this task type.   Video frame object tracking (VideoObjectTracking), and adjustment and verification (AdjustmentVideoObjectTracking) labeling jobs for this task type.   3D point cloud semantic segmentation (3DPointCloudSemanticSegmentation), and adjustment and verification (Adjustment3DPointCloudSemanticSegmentation) labeling jobs for this task type.    3D point cloud object tracking (3DPointCloudObjectTracking), and adjustment and verification (Adjustment3DPointCloudObjectTracking) labeling jobs for this task type.        If you are creating an adjustment or verification labeling job, you must use a different LabelAttributeName than the one used in the original labeling job. The original labeling job is the Ground Truth labeling job that produced the labels that you want verified or adjusted. To learn more about adjustment and verification labeling jobs, see Verify and Adjust Labels.
             input_config: Input data for the labeling job, such as the Amazon S3 location of the data objects and the location of the manifest file that describes the data objects. You must specify at least one of the following: S3DataSource or SnsDataSource.    Use SnsDataSource to specify an SNS input topic for a streaming labeling job. If you do not specify and SNS input topic ARN, Ground Truth will create a one-time labeling job that stops after all data objects in the input manifest file have been labeled.   Use S3DataSource to specify an input manifest file for both streaming and one-time labeling jobs. Adding an S3DataSource is optional if you use SnsDataSource to create a streaming labeling job.   If you use the Amazon Mechanical Turk workforce, your input data should not include confidential information, personal information or protected health information. Use ContentClassifiers to specify that your data is free of personally identifiable information and adult content.
             output_config: The location of the output data and the Amazon Web Services Key Management Service key ID for the key used to encrypt the output data, if any.
             role_arn: The Amazon Resource Number (ARN) that Amazon SageMaker assumes to perform tasks on your behalf during data labeling. You must grant this role the necessary permissions so that Amazon SageMaker can successfully complete data labeling.
@@ -28891,6 +28893,9 @@ class TrainingPlan(Base):
         total_instance_count: The total number of instances reserved in this training plan.
         available_instance_count: The number of instances currently available for use in this training plan.
         in_use_instance_count: The number of instances currently in use from this training plan.
+        unhealthy_instance_count: The number of instances in the training plan that are currently in an unhealthy state.
+        available_spare_instance_count: The number of available spare instances in the training plan.
+        total_ultra_server_count: The total number of UltraServers reserved to this training plan.
         target_resources: The target resources (e.g., SageMaker Training Jobs, SageMaker HyperPod) 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.
         reserved_capacity_summaries: The list of Reserved Capacity providing the underlying compute resources of the plan.
 
@@ -28909,6 +28914,9 @@ class TrainingPlan(Base):
     total_instance_count: Optional[int] = Unassigned()
     available_instance_count: Optional[int] = Unassigned()
     in_use_instance_count: Optional[int] = Unassigned()
+    unhealthy_instance_count: Optional[int] = Unassigned()
+    available_spare_instance_count: Optional[int] = Unassigned()
+    total_ultra_server_count: Optional[int] = Unassigned()
     target_resources: Optional[List[str]] = Unassigned()
     reserved_capacity_summaries: Optional[List[shapes.ReservedCapacitySummary]] = Unassigned()
 
@@ -28934,6 +28942,7 @@ class TrainingPlan(Base):
         cls,
         training_plan_name: str,
         training_plan_offering_id: str,
+        spare_instance_count_per_ultra_server: Optional[int] = Unassigned(),
         tags: Optional[List[shapes.Tag]] = Unassigned(),
         session: Optional[Session] = None,
         region: Optional[str] = None,
@@ -28944,6 +28953,7 @@ class TrainingPlan(Base):
         Parameters:
             training_plan_name: The name of the training plan to create.
             training_plan_offering_id: The unique identifier of the training plan offering to use for creating this plan.
+            spare_instance_count_per_ultra_server: Number of spare instances to reserve per UltraServer for enhanced resiliency. Default is 1.
             tags: An array of key-value pairs to apply to this training plan.
             session: Boto3 session.
             region: Region name.
@@ -28977,6 +28987,7 @@ class TrainingPlan(Base):
         operation_input_args = {
             "TrainingPlanName": training_plan_name,
             "TrainingPlanOfferingId": training_plan_offering_id,
+            "SpareInstanceCountPerUltraServer": spare_instance_count_per_ultra_server,
             "Tags": tags,
         }
 

{sagemaker_core-1.0.49 → sagemaker_core-1.0.51}/src/sagemaker_core/main/shapes.py

@@ -1020,6 +1020,36 @@ class InstanceGroup(Base):
     instance_group_name: str
 
 
+class PlacementSpecification(Base):
+    """
+    PlacementSpecification
+      Specifies how instances should be placed on a specific UltraServer.
+
+    Attributes
+    ----------------------
+    ultra_server_id: The unique identifier of the UltraServer where instances should be placed.
+    instance_count: The number of ML compute instances required to be placed together on the same UltraServer. Minimum value of 1.
+    """
+
+    instance_count: int
+    ultra_server_id: Optional[str] = Unassigned()
+
+
+class InstancePlacementConfig(Base):
+    """
+    InstancePlacementConfig
+      Configuration for how instances are placed and allocated within UltraServers. This is only applicable for UltraServer capacity.
+
+    Attributes
+    ----------------------
+    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.
+    placement_specifications: A list of specifications for how instances should be placed on specific UltraServers. Maximum of 10 items is supported.
+    """
+
+    enable_multiple_jobs: Optional[bool] = Unassigned()
+    placement_specifications: Optional[List[PlacementSpecification]] = Unassigned()
+
+
 class ResourceConfig(Base):
     """
     ResourceConfig
@@ -1034,6 +1064,7 @@ class ResourceConfig(Base):
     keep_alive_period_in_seconds: The duration of time in seconds to retain configured resources in a warm pool for subsequent training jobs.
     instance_groups: The configuration of a heterogeneous cluster in JSON format.
     training_plan_arn: The Amazon Resource Name (ARN); of the training plan to use for this resource configuration.
+    instance_placement_config: Configuration for how training job instances are placed and allocated within UltraServers. Only applicable for UltraServer capacity.
     """
 
     volume_size_in_gb: int
@@ -1043,6 +1074,7 @@ class ResourceConfig(Base):
     keep_alive_period_in_seconds: Optional[int] = Unassigned()
     instance_groups: Optional[List[InstanceGroup]] = Unassigned()
     training_plan_arn: Optional[str] = Unassigned()
+    instance_placement_config: Optional[InstancePlacementConfig] = Unassigned()
 
 
 class StoppingCondition(Base):
@@ -3390,13 +3422,13 @@ class ClusterEbsVolumeConfig(Base):
 class ClusterMetadata(Base):
     """
     ClusterMetadata
-      Metadata information about a SageMaker HyperPod cluster showing information about the cluster level operations, such as creating, updating, and deleting.
+      Metadata information about a HyperPod cluster showing information about the cluster level operations, such as creating, updating, and deleting.
 
     Attributes
     ----------------------
     failure_message: An error message describing why the cluster level operation (such as creating, updating, or deleting) failed.
-    eks_role_access_entries: A list of Amazon EKS IAM role ARNs associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters.
-    slr_access_entry: The Service-Linked Role (SLR) associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters.
+    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.
+    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.
     """
 
     failure_message: Optional[str] = Unassigned()
@@ -3407,7 +3439,7 @@ class ClusterMetadata(Base):
 class InstanceGroupMetadata(Base):
     """
     InstanceGroupMetadata
-      Metadata information about an instance group in a SageMaker HyperPod cluster.
+      Metadata information about an instance group in a HyperPod cluster.
 
     Attributes
     ----------------------
@@ -3507,11 +3539,11 @@ class ClusterEventDetail(Base):
     Attributes
     ----------------------
     event_id: The unique identifier (UUID) of the event.
-    cluster_arn: The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event.
-    cluster_name: The name of the SageMaker HyperPod cluster associated with the event.
+    cluster_arn: The Amazon Resource Name (ARN) of the HyperPod cluster associated with the event.
+    cluster_name: The name of the HyperPod cluster associated with the event.
     instance_group_name: The name of the instance group associated with the event, if applicable.
     instance_id: The EC2 instance ID associated with the event, if applicable.
-    resource_type: The type of resource associated with the event. Valid values are "Cluster", "InstanceGroup", or "Instance".
+    resource_type: The type of resource associated with the event. Valid values are Cluster, InstanceGroup, or Instance.
     event_time: The timestamp when the event occurred.
     event_details: Additional details about the event, including event-specific metadata.
     description: A human-readable description of the event.
@@ -3531,16 +3563,16 @@ class ClusterEventDetail(Base):
 class ClusterEventSummary(Base):
     """
     ClusterEventSummary
-      A summary of an event in a SageMaker HyperPod cluster.
+      A summary of an event in a HyperPod cluster.
 
     Attributes
     ----------------------
     event_id: The unique identifier (UUID) of the event.
-    cluster_arn: The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event.
-    cluster_name: The name of the SageMaker HyperPod cluster associated with the event.
+    cluster_arn: The Amazon Resource Name (ARN) of the HyperPod cluster associated with the event.
+    cluster_name: The name of the HyperPod cluster associated with the event.
     instance_group_name: The name of the instance group associated with the event, if applicable.
-    instance_id: The EC2 instance ID associated with the event, if applicable.
-    resource_type: The type of resource associated with the event. Valid values are "Cluster", "InstanceGroup", or "Instance".
+    instance_id: The Amazon Elastic Compute Cloud (EC2) instance ID associated with the event, if applicable.
+    resource_type: The type of resource associated with the event. Valid values are Cluster, InstanceGroup, or Instance.
     event_time: The timestamp when the event occurred.
     description: A brief, human-readable description of the event.
     """
@@ -3738,6 +3770,19 @@ class ClusterInstanceStatusDetails(Base):
     message: Optional[str] = Unassigned()
 
 
+class UltraServerInfo(Base):
+    """
+    UltraServerInfo
+      Contains information about the UltraServer object.
+
+    Attributes
+    ----------------------
+    id: The unique identifier of the UltraServer.
+    """
+
+    id: Optional[str] = Unassigned()
+
+
 class ClusterNodeDetails(Base):
     """
     ClusterNodeDetails
@@ -3762,6 +3807,7 @@ class ClusterNodeDetails(Base):
     placement: The placement details of the SageMaker HyperPod cluster node.
     current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the node.
     desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the node.
+    ultra_server_info: Contains information about the UltraServer.
     """
 
     instance_group_name: Optional[str] = Unassigned()
@@ -3781,6 +3827,7 @@ class ClusterNodeDetails(Base):
     placement: Optional[ClusterInstancePlacement] = Unassigned()
     current_image_id: Optional[str] = Unassigned()
     desired_image_id: Optional[str] = Unassigned()
+    ultra_server_info: Optional[UltraServerInfo] = Unassigned()
 
 
 class ClusterNodeSummary(Base):
@@ -3797,6 +3844,7 @@ class ClusterNodeSummary(Base):
     launch_time: The time when the instance is launched.
     last_software_update_time: The time when SageMaker last updated the software of the instances in the cluster.
     instance_status: The status of the instance.
+    ultra_server_info: Contains information about the UltraServer.
     """
 
     instance_group_name: str
@@ -3806,6 +3854,7 @@ class ClusterNodeSummary(Base):
     instance_status: ClusterInstanceStatusDetails
     node_logical_id: Optional[str] = Unassigned()
     last_software_update_time: Optional[datetime.datetime] = Unassigned()
+    ultra_server_info: Optional[UltraServerInfo] = Unassigned()
 
 
 class ClusterOrchestratorEksConfig(Base):
@@ -5298,6 +5347,19 @@ class RStudioServerProDomainSettings(Base):
     default_resource_spec: Optional[ResourceSpec] = Unassigned()
 
 
+class TrustedIdentityPropagationSettings(Base):
+    """
+    TrustedIdentityPropagationSettings
+      The Trusted Identity Propagation (TIP) settings for the SageMaker domain. These settings determine how user identities from IAM Identity Center are propagated through the domain to TIP enabled Amazon Web Services services.
+
+    Attributes
+    ----------------------
+    status: The status of Trusted Identity Propagation (TIP) at the SageMaker domain level.  When disabled, standard IAM role-based access is used.  When enabled:   User identities from IAM Identity Center are propagated through the application to TIP enabled Amazon Web Services services.   New applications or existing applications that are automatically patched, will use the domain level configuration.
+    """
+
+    status: str
+
+
 class DockerSettings(Base):
     """
     DockerSettings
@@ -5350,6 +5412,7 @@ class DomainSettings(Base):
     security_group_ids: The security groups for the Amazon Virtual Private Cloud that the Domain uses for communication between Domain-level apps and user apps.
     r_studio_server_pro_domain_settings: A collection of settings that configure the RStudioServerPro Domain-level app.
     execution_role_identity_config: The configuration for attaching a SageMaker AI user profile name to the execution role as a sts:SourceIdentity key.
+    trusted_identity_propagation_settings: The Trusted Identity Propagation (TIP) settings for the SageMaker domain. These settings determine how user identities from IAM Identity Center are propagated through the domain to TIP enabled Amazon Web Services services.
     docker_settings: A collection of settings that configure the domain's Docker interaction.
     amazon_q_settings: A collection of settings that configure the Amazon Q experience within the domain. The AuthMode that you use to create the domain must be SSO.
     unified_studio_settings: The settings that apply to an SageMaker AI domain when you use it in Amazon SageMaker Unified Studio.
@@ -5358,6 +5421,9 @@ class DomainSettings(Base):
     security_group_ids: Optional[List[str]] = Unassigned()
     r_studio_server_pro_domain_settings: Optional[RStudioServerProDomainSettings] = Unassigned()
     execution_role_identity_config: Optional[str] = Unassigned()
+    trusted_identity_propagation_settings: Optional[TrustedIdentityPropagationSettings] = (
+        Unassigned()
+    )
     docker_settings: Optional[DockerSettings] = Unassigned()
     amazon_q_settings: Optional[AmazonQSettings] = Unassigned()
     unified_studio_settings: Optional[UnifiedStudioSettings] = Unassigned()
@@ -9638,6 +9704,27 @@ class TemplateProviderDetail(Base):
     cfn_template_provider_detail: Optional[CfnTemplateProviderDetail] = Unassigned()
 
 
+class UltraServerSummary(Base):
+    """
+    UltraServerSummary
+      A summary of UltraServer resources and their current status.
+
+    Attributes
+    ----------------------
+    ultra_server_type: The type of UltraServer, such as ml.u-p6e-gb200x72.
+    instance_type: The Amazon EC2 instance type used in the UltraServer.
+    ultra_server_count: The number of UltraServers of this type.
+    available_spare_instance_count: The number of available spare instances in the UltraServers.
+    unhealthy_instance_count: The total number of instances across all UltraServers of this type that are currently in an unhealthy state.
+    """
+
+    ultra_server_type: str
+    instance_type: str
+    ultra_server_count: Optional[int] = Unassigned()
+    available_spare_instance_count: Optional[int] = Unassigned()
+    unhealthy_instance_count: Optional[int] = Unassigned()
+
+
 class SubscribedWorkteam(Base):
     """
     SubscribedWorkteam
@@ -9741,6 +9828,9 @@ class ReservedCapacitySummary(Base):
     Attributes
     ----------------------
     reserved_capacity_arn: The Amazon Resource Name (ARN); of the reserved capacity.
+    reserved_capacity_type: The type of reserved capacity.
+    ultra_server_type: The type of UltraServer included in this reserved capacity, such as ml.u-p6e-gb200x72.
+    ultra_server_count: The number of UltraServers included in this reserved capacity.
     instance_type: The instance type for the reserved capacity.
     total_instance_count: The total number of instances in the reserved capacity.
     status: The current status of the reserved capacity.
@@ -9755,6 +9845,9 @@ class ReservedCapacitySummary(Base):
     instance_type: str
     total_instance_count: int
     status: str
+    reserved_capacity_type: Optional[str] = Unassigned()
+    ultra_server_type: Optional[str] = Unassigned()
+    ultra_server_count: Optional[int] = Unassigned()
     availability_zone: Optional[str] = Unassigned()
     duration_hours: Optional[int] = Unassigned()
     duration_minutes: Optional[int] = Unassigned()
@@ -10153,6 +10246,7 @@ class DomainSettingsForUpdate(Base):
     r_studio_server_pro_domain_settings_for_update: A collection of RStudioServerPro Domain-level app settings to update. A single RStudioServerPro application is created for a domain.
     execution_role_identity_config: The configuration for attaching a SageMaker AI user profile name to the execution role as a sts:SourceIdentity key. This configuration can only be modified if there are no apps in the InService or Pending state.
     security_group_ids: The security groups for the Amazon Virtual Private Cloud that the Domain uses for communication between Domain-level apps and user apps.
+    trusted_identity_propagation_settings: The Trusted Identity Propagation (TIP) settings for the SageMaker domain. These settings determine how user identities from IAM Identity Center are propagated through the domain to TIP enabled Amazon Web Services services.
     docker_settings: A collection of settings that configure the domain's Docker interaction.
     amazon_q_settings: A collection of settings that configure the Amazon Q experience within the domain.
     unified_studio_settings: The settings that apply to an SageMaker AI domain when you use it in Amazon SageMaker Unified Studio.
@@ -10163,6 +10257,9 @@ class DomainSettingsForUpdate(Base):
     ] = Unassigned()
     execution_role_identity_config: Optional[str] = Unassigned()
     security_group_ids: Optional[List[str]] = Unassigned()
+    trusted_identity_propagation_settings: Optional[TrustedIdentityPropagationSettings] = (
+        Unassigned()
+    )
     docker_settings: Optional[DockerSettings] = Unassigned()
     amazon_q_settings: Optional[AmazonQSettings] = Unassigned()
     unified_studio_settings: Optional[UnifiedStudioSettings] = Unassigned()
@@ -12207,6 +12304,7 @@ class TrainingPlanSummary(Base):
     total_instance_count: The total number of instances reserved in this training plan.
     available_instance_count: The number of instances currently available for use in this training plan.
     in_use_instance_count: The number of instances currently in use from this training plan.
+    total_ultra_server_count: The total number of UltraServers allocated to this training plan.
     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.
     reserved_capacity_summaries: A list of reserved capacities associated with this training plan, including details such as instance types, counts, and availability zones.
     """
@@ -12224,6 +12322,7 @@ class TrainingPlanSummary(Base):
     total_instance_count: Optional[int] = Unassigned()
     available_instance_count: Optional[int] = Unassigned()
     in_use_instance_count: Optional[int] = Unassigned()
+    total_ultra_server_count: Optional[int] = Unassigned()
     target_resources: Optional[List[str]] = Unassigned()
     reserved_capacity_summaries: Optional[List[ReservedCapacitySummary]] = Unassigned()
 
@@ -12309,6 +12408,39 @@ class TrialSummary(Base):
     last_modified_time: Optional[datetime.datetime] = Unassigned()
 
 
+class UltraServer(Base):
+    """
+    UltraServer
+      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.
+
+    Attributes
+    ----------------------
+    ultra_server_id: The unique identifier for the UltraServer.
+    ultra_server_type: The type of UltraServer, such as ml.u-p6e-gb200x72.
+    availability_zone: The name of the Availability Zone where the UltraServer is provisioned.
+    instance_type: The Amazon EC2 instance type used in the UltraServer.
+    total_instance_count: The total number of instances in this UltraServer.
+    configured_spare_instance_count: The number of spare instances configured for this UltraServer to provide enhanced resiliency.
+    available_instance_count: The number of instances currently available for use in this UltraServer.
+    in_use_instance_count: The number of instances currently in use in this UltraServer.
+    available_spare_instance_count: The number of available spare instances in the UltraServer.
+    unhealthy_instance_count: The number of instances in this UltraServer that are currently in an unhealthy state.
+    health_status: The overall health status of the UltraServer.
+    """
+
+    ultra_server_id: str
+    ultra_server_type: str
+    availability_zone: str
+    instance_type: str
+    total_instance_count: int
+    configured_spare_instance_count: Optional[int] = Unassigned()
+    available_instance_count: Optional[int] = Unassigned()
+    in_use_instance_count: Optional[int] = Unassigned()
+    available_spare_instance_count: Optional[int] = Unassigned()
+    unhealthy_instance_count: Optional[int] = Unassigned()
+    health_status: Optional[str] = Unassigned()
+
+
 class UserProfileDetails(Base):
     """
     UserProfileDetails
@@ -13028,6 +13160,9 @@ class ReservedCapacityOffering(Base):
 
     Attributes
     ----------------------
+    reserved_capacity_type: The type of reserved capacity offering.
+    ultra_server_type: The type of UltraServer included in this reserved capacity offering, such as ml.u-p6e-gb200x72.
+    ultra_server_count: The number of UltraServers included in this reserved capacity offering.
     instance_type: The instance type for the reserved capacity offering.
     instance_count: The number of instances in the reserved capacity offering.
     availability_zone: The availability zone for the reserved capacity offering.
@@ -13039,6 +13174,9 @@ class ReservedCapacityOffering(Base):
 
     instance_type: str
     instance_count: int
+    reserved_capacity_type: Optional[str] = Unassigned()
+    ultra_server_type: Optional[str] = Unassigned()
+    ultra_server_count: Optional[int] = Unassigned()
     availability_zone: Optional[str] = Unassigned()
     duration_hours: Optional[int] = Unassigned()
     duration_minutes: Optional[int] = Unassigned()

{sagemaker_core-1.0.49 → sagemaker_core-1.0.51/src/sagemaker_core.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sagemaker-core
-Version: 1.0.49
+Version: 1.0.51
 Summary: An python package for sagemaker core functionalities
 Author-email: AWS <sagemaker-interests@amazon.com>
 Project-URL: Repository, https://github.com/aws/sagemaker-core.git

sagemaker_core-1.0.49/VERSION

@@ -1 +0,0 @@
-1.0.49