sagemaker-core 1.0.47__py3-none-any.whl → 1.0.62__py3-none-any.whl

sagemaker_core/main/shapes.py

@@ -66,7 +66,7 @@ class InvokeEndpointAsyncOutput(Base):
 
     Attributes
     ----------------------
-    inference_id: Identifier for an inference request. This will be the same as the InferenceId specified in the input. Amazon SageMaker will generate an identifier for you if you do not specify one.
+    inference_id: Identifier for an inference request. This will be the same as the InferenceId specified in the input. Amazon SageMaker AI will generate an identifier for you if you do not specify one.
     output_location: The Amazon S3 URI where the inference response payload is stored.
     failure_location: The Amazon S3 URI where the inference failure response payload is stored.
     """
@@ -85,7 +85,7 @@ class InvokeEndpointOutput(Base):
     body: Includes the inference provided by the model.  For information about the format of the response body, see Common Data Formats-Inference. If the explainer is activated, the body includes the explanations provided by the model. For more information, see the Response section under Invoke the Endpoint in the Developer Guide.
     content_type: The MIME type of the inference returned from the model container.
     invoked_production_variant: Identifies the production variant that was invoked.
-    custom_attributes: Provides additional information in the response about the inference returned by a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to return an ID received in the CustomAttributes header of a request or other metadata that a service endpoint was programmed to produce. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1). If the customer wants the custom attribute returned, the model must set the custom attribute to be included on the way back.  The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with Trace ID: in your post-processing function. This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
+    custom_attributes: Provides additional information in the response about the inference returned by a model hosted at an Amazon SageMaker AI endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to return an ID received in the CustomAttributes header of a request or other metadata that a service endpoint was programmed to produce. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1). If the customer wants the custom attribute returned, the model must set the custom attribute to be included on the way back.  The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with Trace ID: in your post-processing function. This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker AI Python SDK.
     new_session_id: If you created a stateful session with your request, the ID and expiration time that the model assigns to that session.
     closed_session_id: If you closed a stateful session with your request, the ID of that session.
     """
@@ -114,12 +114,12 @@ class PayloadPart(Base):
 class ModelStreamError(Base):
     """
     ModelStreamError
-       An error occurred while streaming the response body. This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
+       An error occurred while streaming the response body. This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker AI.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
 
     Attributes
     ----------------------
     message
-    error_code: This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
+    error_code: This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker AI.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
     """
 
     message: Optional[str] = Unassigned()
@@ -134,7 +134,7 @@ class ResponseStream(Base):
     Attributes
     ----------------------
     payload_part: A wrapper for pieces of the payload that's returned in response to a streaming inference request. A streaming inference response consists of one or more payload parts.
-    model_stream_error:  An error occurred while streaming the response body. This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
+    model_stream_error:  An error occurred while streaming the response body. This error can have the following error codes:  ModelInvocationTimeExceeded  The model failed to finish sending the response within the timeout period allowed by Amazon SageMaker AI.  StreamBroken  The Transmission Control Protocol (TCP) connection between the client and the model was reset or closed.
     internal_stream_failure: The stream processing failed because of an unknown error, exception or failure. Try your request again.
     """
 
@@ -152,7 +152,7 @@ class InvokeEndpointWithResponseStreamOutput(Base):
     body
     content_type: The MIME type of the inference returned from the model container.
     invoked_production_variant: Identifies the production variant that was invoked.
-    custom_attributes: Provides additional information in the response about the inference returned by a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to return an ID received in the CustomAttributes header of a request or other metadata that a service endpoint was programmed to produce. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1). If the customer wants the custom attribute returned, the model must set the custom attribute to be included on the way back.  The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with Trace ID: in your post-processing function. This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
+    custom_attributes: Provides additional information in the response about the inference returned by a model hosted at an Amazon SageMaker AI endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to return an ID received in the CustomAttributes header of a request or other metadata that a service endpoint was programmed to produce. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1). If the customer wants the custom attribute returned, the model must set the custom attribute to be included on the way back.  The code in your model is responsible for setting or updating any custom attributes in the response. If your code does not set this value in the response, an empty value is returned. For example, if a custom attribute represents the trace ID, your model can prepend the custom attribute with Trace ID: in your post-processing function. This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker AI Python SDK.
     """
 
     body: ResponseStream
@@ -494,6 +494,21 @@ class ActionSummary(Base):
     last_modified_time: Optional[datetime.datetime] = Unassigned()
 
 
+class AddClusterNodeSpecification(Base):
+    """
+    AddClusterNodeSpecification
+      Specifies an instance group and the number of nodes to add to it.
+
+    Attributes
+    ----------------------
+    instance_group_name: The name of the instance group to which you want to add nodes.
+    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.
+    """
+
+    instance_group_name: str
+    increment_target_count_by: int
+
+
 class Tag(Base):
     """
     Tag
@@ -509,6 +524,19 @@ class Tag(Base):
     value: str
 
 
+class AdditionalEnis(Base):
+    """
+    AdditionalEnis
+      Information about additional Elastic Network Interfaces (ENIs) associated with an instance.
+
+    Attributes
+    ----------------------
+    efa_enis: A list of Elastic Fabric Adapter (EFA) ENIs associated with the instance.
+    """
+
+    efa_enis: Optional[List[str]] = Unassigned()
+
+
 class ModelAccessConfig(Base):
     """
     ModelAccessConfig
@@ -992,6 +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
@@ -1006,6 +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
@@ -1015,6 +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):
@@ -2400,6 +2460,42 @@ class Autotune(Base):
     mode: str
 
 
+class BatchAddClusterNodesError(Base):
+    """
+    BatchAddClusterNodesError
+      Information about an error that occurred during the node addition operation.
+
+    Attributes
+    ----------------------
+    instance_group_name: The name of the instance group for which the error occurred.
+    error_code: The error code associated with the failure. Possible values include InstanceGroupNotFound and InvalidInstanceGroupState.
+    failed_count: The number of nodes that failed to be added to the specified instance group.
+    message: A descriptive message providing additional details about the error.
+    """
+
+    instance_group_name: str
+    error_code: str
+    failed_count: int
+    message: Optional[str] = Unassigned()
+
+
+class NodeAdditionResult(Base):
+    """
+    NodeAdditionResult
+      Information about a node that was successfully added to the cluster.
+
+    Attributes
+    ----------------------
+    node_logical_id: A unique identifier assigned to the node that can be used to track its provisioning status through the DescribeClusterNode operation.
+    instance_group_name: The name of the instance group to which the node was added.
+    status: The current status of the node. Possible values include Pending, Running, Failed, ShuttingDown, SystemUpdating, DeepHealthCheckInProgress, and NotFound.
+    """
+
+    node_logical_id: str
+    instance_group_name: str
+    status: str
+
+
 class BatchDataCaptureConfig(Base):
     """
     BatchDataCaptureConfig
@@ -2417,6 +2513,23 @@ class BatchDataCaptureConfig(Base):
     generate_inference_id: Optional[bool] = Unassigned()
 
 
+class BatchDeleteClusterNodeLogicalIdsError(Base):
+    """
+    BatchDeleteClusterNodeLogicalIdsError
+      Information about an error that occurred when attempting to delete a node identified by its NodeLogicalId.
+
+    Attributes
+    ----------------------
+    code: The error code associated with the failure. Possible values include NodeLogicalIdNotFound, InvalidNodeStatus, and InternalError.
+    message: A descriptive message providing additional details about the error.
+    node_logical_id: The NodeLogicalId of the node that could not be deleted.
+    """
+
+    code: str
+    message: str
+    node_logical_id: str
+
+
 class BatchDeleteClusterNodesError(Base):
     """
     BatchDeleteClusterNodesError
@@ -2442,10 +2555,14 @@ class BatchDeleteClusterNodesResponse(Base):
     ----------------------
     failed: A list of errors encountered when deleting the specified nodes.
     successful: A list of node IDs that were successfully deleted from the specified cluster.
+    failed_node_logical_ids: A list of NodeLogicalIds that could not be deleted, along with error information explaining why the deletion failed.
+    successful_node_logical_ids: A list of NodeLogicalIds that were successfully deleted from the cluster.
     """
 
     failed: Optional[List[BatchDeleteClusterNodesError]] = Unassigned()
     successful: Optional[List[str]] = Unassigned()
+    failed_node_logical_ids: Optional[List[BatchDeleteClusterNodeLogicalIdsError]] = Unassigned()
+    successful_node_logical_ids: Optional[List[str]] = Unassigned()
 
 
 class BatchDescribeModelPackageError(Base):
@@ -2901,6 +3018,21 @@ class CanvasAppSettings(Base):
     emr_serverless_settings: Optional[EmrServerlessSettings] = Unassigned()
 
 
+class CapacityReservation(Base):
+    """
+    CapacityReservation
+      Information about the Capacity Reservation used by an instance or instance group.
+
+    Attributes
+    ----------------------
+    arn: The Amazon Resource Name (ARN) of the Capacity Reservation.
+    type: The type of Capacity Reservation. Valid values are ODCR (On-Demand Capacity Reservation) or CRG (Capacity Reservation Group).
+    """
+
+    arn: Optional[str] = Unassigned()
+    type: Optional[str] = Unassigned()
+
+
 class CapacitySizeConfig(Base):
     """
     CapacitySizeConfig
@@ -3274,6 +3406,40 @@ class ClarifyExplainerConfig(Base):
     inference_config: Optional[ClarifyInferenceConfig] = Unassigned()
 
 
+class ClusterAutoScalingConfig(Base):
+    """
+    ClusterAutoScalingConfig
+      Specifies the autoscaling configuration for a HyperPod cluster.
+
+    Attributes
+    ----------------------
+    mode: Describes whether autoscaling is enabled or disabled for the cluster. Valid values are Enable and Disable.
+    auto_scaler_type: The type of autoscaler to use. Currently supported value is Karpenter.
+    """
+
+    mode: str
+    auto_scaler_type: Optional[str] = Unassigned()
+
+
+class ClusterAutoScalingConfigOutput(Base):
+    """
+    ClusterAutoScalingConfigOutput
+      The autoscaling configuration and status information for a HyperPod cluster.
+
+    Attributes
+    ----------------------
+    mode: Describes whether autoscaling is enabled or disabled for the cluster.
+    auto_scaler_type: The type of autoscaler configured for the cluster.
+    status: The current status of the autoscaling configuration. Valid values are InService, Failed, Creating, and Deleting.
+    failure_message: If the autoscaling status is Failed, this field contains a message describing the failure.
+    """
+
+    mode: str
+    status: str
+    auto_scaler_type: Optional[str] = Unassigned()
+    failure_message: Optional[str] = Unassigned()
+
+
 class ClusterEbsVolumeConfig(Base):
     """
     ClusterEbsVolumeConfig
@@ -3282,9 +3448,181 @@ class ClusterEbsVolumeConfig(Base):
     Attributes
     ----------------------
     volume_size_in_gb: The size in gigabytes (GB) of the additional EBS volume to be attached to the instances in the SageMaker HyperPod cluster instance group. The additional EBS volume is attached to each instance within the SageMaker HyperPod cluster instance group and mounted to /opt/sagemaker.
+    volume_kms_key_id: The ID of a KMS key to encrypt the Amazon EBS volume.
+    root_volume: Specifies whether the configuration is for the cluster's root or secondary Amazon EBS volume. You can specify two ClusterEbsVolumeConfig fields to configure both the root and secondary volumes. Set the value to True if you'd like to provide your own customer managed Amazon Web Services KMS key to encrypt the root volume. When True:   The configuration is applied to the root volume.   You can't specify the VolumeSizeInGB field. The size of the root volume is determined for you.   You must specify a KMS key ID for VolumeKmsKeyId to encrypt the root volume with your own KMS key instead of an Amazon Web Services owned KMS key.   Otherwise, by default, the value is False, and the following applies:   The configuration is applied to the secondary volume, while the root volume is encrypted with an Amazon Web Services owned key.   You must specify the VolumeSizeInGB field.   You can optionally specify the VolumeKmsKeyId to encrypt the secondary volume with your own KMS key instead of an Amazon Web Services owned KMS key.
     """
 
     volume_size_in_gb: Optional[int] = Unassigned()
+    volume_kms_key_id: Optional[str] = Unassigned()
+    root_volume: Optional[bool] = Unassigned()
+
+
+class ClusterMetadata(Base):
+    """
+    ClusterMetadata
+      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 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()
+    eks_role_access_entries: Optional[List[str]] = Unassigned()
+    slr_access_entry: Optional[str] = Unassigned()
+
+
+class InstanceGroupMetadata(Base):
+    """
+    InstanceGroupMetadata
+      Metadata information about an instance group in a HyperPod cluster.
+
+    Attributes
+    ----------------------
+    failure_message: An error message describing why the instance group level operation (such as creating, scaling, or deleting) failed.
+    availability_zone_id: The ID of the Availability Zone where the instance group is located.
+    capacity_reservation: Information about the Capacity Reservation used by the instance group.
+    subnet_id: The ID of the subnet where the instance group is located.
+    security_group_ids: A list of security group IDs associated with the instance group.
+    ami_override: If you use a custom Amazon Machine Image (AMI) for the instance group, this field shows the ID of the custom AMI.
+    """
+
+    failure_message: Optional[str] = Unassigned()
+    availability_zone_id: Optional[str] = Unassigned()
+    capacity_reservation: Optional[CapacityReservation] = Unassigned()
+    subnet_id: Optional[str] = Unassigned()
+    security_group_ids: Optional[List[str]] = Unassigned()
+    ami_override: Optional[str] = Unassigned()
+
+
+class InstanceGroupScalingMetadata(Base):
+    """
+    InstanceGroupScalingMetadata
+      Metadata information about scaling operations for an instance group.
+
+    Attributes
+    ----------------------
+    instance_count: The current number of instances in the group.
+    target_count: The desired number of instances for the group after scaling.
+    failure_message: An error message describing why the scaling operation failed, if applicable.
+    """
+
+    instance_count: Optional[int] = Unassigned()
+    target_count: Optional[int] = Unassigned()
+    failure_message: Optional[str] = Unassigned()
+
+
+class InstanceMetadata(Base):
+    """
+    InstanceMetadata
+      Metadata information about an instance in a HyperPod cluster.
+
+    Attributes
+    ----------------------
+    customer_eni: The ID of the customer-managed Elastic Network Interface (ENI) associated with the instance.
+    additional_enis: Information about additional Elastic Network Interfaces (ENIs) associated with the instance.
+    capacity_reservation: Information about the Capacity Reservation used by the instance.
+    failure_message: An error message describing why the instance creation or update failed, if applicable.
+    lcs_execution_state: The execution state of the Lifecycle Script (LCS) for the instance.
+    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.
+    """
+
+    customer_eni: Optional[str] = Unassigned()
+    additional_enis: Optional[AdditionalEnis] = Unassigned()
+    capacity_reservation: Optional[CapacityReservation] = Unassigned()
+    failure_message: Optional[str] = Unassigned()
+    lcs_execution_state: Optional[str] = Unassigned()
+    node_logical_id: Optional[str] = Unassigned()
+
+
+class EventMetadata(Base):
+    """
+    EventMetadata
+      Metadata associated with a cluster event, which may include details about various resource types.
+
+    Attributes
+    ----------------------
+    cluster: Metadata specific to cluster-level events.
+    instance_group: Metadata specific to instance group-level events.
+    instance_group_scaling: Metadata related to instance group scaling events.
+    instance: Metadata specific to instance-level events.
+    """
+
+    cluster: Optional[ClusterMetadata] = Unassigned()
+    instance_group: Optional[InstanceGroupMetadata] = Unassigned()
+    instance_group_scaling: Optional[InstanceGroupScalingMetadata] = Unassigned()
+    instance: Optional[InstanceMetadata] = Unassigned()
+
+
+class EventDetails(Base):
+    """
+    EventDetails
+      Detailed information about a specific event, including event metadata.
+
+    Attributes
+    ----------------------
+    event_metadata: Metadata specific to the event, which may include information about the cluster, instance group, or instance involved.
+    """
+
+    event_metadata: Optional[EventMetadata] = Unassigned()
+
+
+class ClusterEventDetail(Base):
+    """
+    ClusterEventDetail
+      Detailed information about a specific event in a HyperPod cluster.
+
+    Attributes
+    ----------------------
+    event_id: The unique identifier (UUID) of 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.
+    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.
+    """
+
+    event_id: str
+    cluster_arn: str
+    cluster_name: Union[str, object]
+    resource_type: str
+    event_time: datetime.datetime
+    instance_group_name: Optional[str] = Unassigned()
+    instance_id: Optional[str] = Unassigned()
+    event_details: Optional[EventDetails] = Unassigned()
+    description: Optional[str] = Unassigned()
+
+
+class ClusterEventSummary(Base):
+    """
+    ClusterEventSummary
+      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 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 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.
+    """
+
+    event_id: str
+    cluster_arn: str
+    cluster_name: Union[str, object]
+    resource_type: str
+    event_time: datetime.datetime
+    instance_group_name: Optional[str] = Unassigned()
+    instance_id: Optional[str] = Unassigned()
+    description: Optional[str] = Unassigned()
 
 
 class ClusterLifeCycleConfig(Base):
@@ -3383,6 +3721,8 @@ class ClusterInstanceGroupDetails(Base):
     training_plan_status: The current status of the training plan associated with this cluster instance group.
     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.
     scheduled_update_config: The configuration object of the schedule that SageMaker follows when updating the AMI.
+    current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the instance group.
+    desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the instance group.
     """
 
     current_count: Optional[int] = Unassigned()
@@ -3399,6 +3739,8 @@ class ClusterInstanceGroupDetails(Base):
     training_plan_status: Optional[str] = Unassigned()
     override_vpc_config: Optional[VpcConfig] = Unassigned()
     scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned()
+    current_image_id: Optional[str] = Unassigned()
+    desired_image_id: Optional[str] = Unassigned()
 
 
 class ClusterInstanceGroupSpecification(Base):
@@ -3419,6 +3761,7 @@ class ClusterInstanceGroupSpecification(Base):
     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 .
     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.
     scheduled_update_config: The configuration object of the schedule that SageMaker uses to update the AMI.
+    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   If 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. Note that if you don't specify an instance group in your UpdateClusterSoftware request, then all of the instance groups are patched with the specified image.
     """
 
     instance_count: int
@@ -3432,6 +3775,7 @@ class ClusterInstanceGroupSpecification(Base):
     training_plan_arn: Optional[str] = Unassigned()
     override_vpc_config: Optional[VpcConfig] = Unassigned()
     scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned()
+    image_id: Optional[str] = Unassigned()
 
 
 class ClusterInstancePlacement(Base):
@@ -3464,6 +3808,19 @@ 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
@@ -3473,6 +3830,7 @@ class ClusterNodeDetails(Base):
     ----------------------
     instance_group_name: The instance group name in which the instance is.
     instance_id: The ID of the instance.
+    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.
     instance_status: The status of the instance.
     instance_type: The type of the instance.
     launch_time: The time when the instance is launched.
@@ -3485,10 +3843,14 @@ class ClusterNodeDetails(Base):
     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.
     private_dns_hostname: The private DNS hostname of the SageMaker HyperPod cluster node.
     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()
     instance_id: Optional[str] = Unassigned()
+    node_logical_id: Optional[str] = Unassigned()
     instance_status: Optional[ClusterInstanceStatusDetails] = Unassigned()
     instance_type: Optional[str] = Unassigned()
     launch_time: Optional[datetime.datetime] = Unassigned()
@@ -3501,6 +3863,9 @@ class ClusterNodeDetails(Base):
     private_primary_ipv6: Optional[str] = Unassigned()
     private_dns_hostname: Optional[str] = Unassigned()
     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):
@@ -3512,10 +3877,12 @@ class ClusterNodeSummary(Base):
     ----------------------
     instance_group_name: The name of the instance group in which the instance is.
     instance_id: The ID of the instance.
+    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.
     instance_type: The type of the instance.
     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
@@ -3523,7 +3890,9 @@ class ClusterNodeSummary(Base):
     instance_type: str
     launch_time: datetime.datetime
     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):
@@ -3715,6 +4084,21 @@ class ClusterSummary(Base):
     training_plan_arns: Optional[List[str]] = Unassigned()
 
 
+class ClusterTieredStorageConfig(Base):
+    """
+    ClusterTieredStorageConfig
+      Defines the configuration for managed tier checkpointing in a HyperPod cluster. Managed tier checkpointing uses multiple storage tiers, including cluster CPU memory, to provide faster checkpoint operations and improved fault tolerance for large-scale model training. The system automatically saves checkpoints at high frequency to memory and periodically persists them to durable storage, like Amazon S3.
+
+    Attributes
+    ----------------------
+    mode: Specifies whether managed tier checkpointing is enabled or disabled for the HyperPod cluster. When set to Enable, the system installs a memory management daemon that provides disaggregated memory as a service for checkpoint storage. When set to Disable, the feature is turned off and the memory management daemon is removed from the cluster.
+    instance_memory_allocation_percentage: The percentage (int) of cluster memory to allocate for checkpointing.
+    """
+
+    mode: str
+    instance_memory_allocation_percentage: Optional[int] = Unassigned()
+
+
 class CustomImage(Base):
     """
     CustomImage
@@ -3919,10 +4303,16 @@ class ComputeQuotaResourceConfig(Base):
     ----------------------
     instance_type: The instance type of the instance group for the cluster.
     count: The number of instances to add to the instance group of a SageMaker HyperPod cluster.
+    accelerators: The number of accelerators to allocate. If you don't specify a value for vCPU and MemoryInGiB, SageMaker AI automatically allocates ratio-based values for those parameters based on the number of accelerators you provide. For example, if you allocate 16 out of 32 total accelerators, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU and MemoryInGiB.
+    v_cpu: The number of vCPU to allocate. If you specify a value only for vCPU, SageMaker AI automatically allocates ratio-based values for MemoryInGiB based on this vCPU parameter. For example, if you allocate 20 out of 40 total vCPU, SageMaker AI uses the ratio of 0.5 and allocates values to MemoryInGiB. Accelerators are set to 0.
+    memory_in_gi_b: The amount of memory in GiB to allocate. If you specify a value only for this parameter, SageMaker AI automatically allocates a ratio-based value for vCPU based on this memory that you provide. For example, if you allocate 200 out of 400 total memory in GiB, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU. Accelerators are set to 0.
     """
 
     instance_type: str
     count: Optional[int] = Unassigned()
+    accelerators: Optional[int] = Unassigned()
+    v_cpu: Optional[float] = Unassigned()
+    memory_in_gi_b: Optional[float] = Unassigned()
 
 
 class ResourceSharingConfig(Base):
@@ -4895,8 +5285,8 @@ class S3FileSystemConfig(Base):
     s3_uri: The Amazon S3 URI of the S3 file system configuration.
     """
 
+    s3_uri: str
     mount_path: Optional[str] = Unassigned()
-    s3_uri: Optional[str] = Unassigned()
 
 
 class CustomFileSystemConfig(Base):
@@ -5016,6 +5406,19 @@ 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
@@ -5025,10 +5428,12 @@ class DockerSettings(Base):
     ----------------------
     enable_docker_access: Indicates whether the domain can access Docker.
     vpc_only_trusted_accounts: The list of Amazon Web Services accounts that are trusted when the domain is created in VPC-only mode.
+    rootless_docker: Indicates whether to use rootless Docker.
     """
 
     enable_docker_access: Optional[str] = Unassigned()
     vpc_only_trusted_accounts: Optional[List[str]] = Unassigned()
+    rootless_docker: Optional[str] = Unassigned()
 
 
 class UnifiedStudioSettings(Base):
@@ -5045,7 +5450,7 @@ class UnifiedStudioSettings(Base):
     project_id: The ID of the Amazon SageMaker Unified Studio project that corresponds to the domain.
     environment_id: The ID of the environment that Amazon SageMaker Unified Studio associates with the domain.
     project_s3_path: The location where Amazon S3 stores temporary execution data and other artifacts for the project that corresponds to the domain.
-    single_sign_on_application_arn: The ARN of the application managed by SageMaker AI and SageMaker Unified Studio in the Amazon Web Services IAM Identity Center.
+    single_sign_on_application_arn: The ARN of the Amazon DataZone application managed by Amazon SageMaker Unified Studio in the Amazon Web Services IAM Identity Center.
     """
 
     studio_web_portal_access: Optional[str] = Unassigned()
@@ -5068,17 +5473,23 @@ 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.
+    ip_address_type: The IP address type for the domain. Specify ipv4 for IPv4-only connectivity or dualstack for both IPv4 and IPv6 connectivity. When you specify dualstack, the subnet must support IPv6 CIDR blocks. If not specified, defaults to ipv4.
     """
 
     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()
+    ip_address_type: Optional[str] = Unassigned()
 
 
 class DefaultSpaceSettings(Base):
@@ -5966,6 +6377,19 @@ class InferenceComponentComputeResourceRequirements(Base):
     max_memory_required_in_mb: Optional[int] = Unassigned()
 
 
+class InferenceComponentDataCacheConfig(Base):
+    """
+    InferenceComponentDataCacheConfig
+      Settings that affect how the inference component caches data.
+
+    Attributes
+    ----------------------
+    enable_caching: Sets whether the endpoint that hosts the inference component caches the model artifacts and container image. With caching enabled, the endpoint caches this data in each instance that it provisions for the inference component. That way, the inference component deploys faster during the auto scaling process. If caching isn't enabled, the inference component takes longer to deploy because of the time it spends downloading the data.
+    """
+
+    enable_caching: bool
+
+
 class InferenceComponentSpecification(Base):
     """
     InferenceComponentSpecification
@@ -5978,6 +6402,7 @@ class InferenceComponentSpecification(Base):
     startup_parameters: Settings that take effect while the model container starts up.
     compute_resource_requirements: The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component. Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.
     base_inference_component_name: The name of an existing inference component that is to contain the inference component that you're creating with your request. Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component. When you create an adapter inference component, use the Container parameter to specify the location of the adapter artifacts. In the parameter value, use the ArtifactUrl parameter of the InferenceComponentContainerSpecification data type. Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.
+    data_cache_config: Settings that affect how the inference component caches data.
     """
 
     model_name: Optional[Union[str, object]] = Unassigned()
@@ -5987,6 +6412,7 @@ class InferenceComponentSpecification(Base):
         Unassigned()
     )
     base_inference_component_name: Optional[str] = Unassigned()
+    data_cache_config: Optional[InferenceComponentDataCacheConfig] = Unassigned()
 
 
 class InferenceComponentRuntimeConfig(Base):
@@ -7392,7 +7818,7 @@ class ProcessingS3Input(Base):
     local_path: The local path in your container where you want Amazon SageMaker to write input data to. LocalPath is an absolute path to the input data and must begin with /opt/ml/processing/. LocalPath is a required parameter when AppManaged is False (default).
     s3_data_type: Whether you use an S3Prefix or a ManifestFile for the data type. If you choose S3Prefix, S3Uri identifies a key name prefix. Amazon SageMaker uses all objects with the specified key name prefix for the processing job. If you choose ManifestFile, S3Uri identifies an object that is a manifest file containing a list of object keys that you want Amazon SageMaker to use for the processing job.
     s3_input_mode: Whether to use File or Pipe input mode. In File mode, Amazon SageMaker copies the data from the input source onto the local ML storage volume before starting your processing container. This is the most commonly used input mode. In Pipe mode, Amazon SageMaker streams input data from the source directly to your processing container into named pipes without using the ML storage volume.
-    s3_data_distribution_type: Whether to distribute the data from Amazon S3 to all processing instances with FullyReplicated, or whether the data from Amazon S3 is shared by Amazon S3 key, downloading one shard of data to each processing instance.
+    s3_data_distribution_type: Whether to distribute the data from Amazon S3 to all processing instances with FullyReplicated, or whether the data from Amazon S3 is sharded by Amazon S3 key, downloading one shard of data to each processing instance.
     s3_compression_type: Whether to GZIP-decompress the data in Amazon S3 as it is streamed into the processing container. Gzip can only be used when Pipe mode is specified as the S3InputMode. In Pipe mode, Amazon SageMaker streams input data from the source directly to your container without using the EBS volume.
     """
 
@@ -7768,7 +8194,7 @@ class S3FileSystem(Base):
     s3_uri: The Amazon S3 URI that specifies the location in S3 where files are stored, which is mounted within the Studio environment. For example: s3://<bucket-name>/<prefix>/.
     """
 
-    s3_uri: Optional[str] = Unassigned()
+    s3_uri: str
 
 
 class CustomFileSystem(Base):
@@ -8873,6 +9299,19 @@ class InferenceComponentContainerSpecificationSummary(Base):
     environment: Optional[Dict[str, str]] = Unassigned()
 
 
+class InferenceComponentDataCacheConfigSummary(Base):
+    """
+    InferenceComponentDataCacheConfigSummary
+      Settings that affect how the inference component caches data.
+
+    Attributes
+    ----------------------
+    enable_caching: Indicates whether the inference component caches model artifacts as part of the auto scaling process.
+    """
+
+    enable_caching: bool
+
+
 class InferenceComponentSpecificationSummary(Base):
     """
     InferenceComponentSpecificationSummary
@@ -8885,6 +9324,7 @@ class InferenceComponentSpecificationSummary(Base):
     startup_parameters: Settings that take effect while the model container starts up.
     compute_resource_requirements: The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.
     base_inference_component_name: The name of the base inference component that contains this inference component.
+    data_cache_config: Settings that affect how the inference component caches data.
     """
 
     model_name: Optional[Union[str, object]] = Unassigned()
@@ -8894,6 +9334,7 @@ class InferenceComponentSpecificationSummary(Base):
         Unassigned()
     )
     base_inference_component_name: Optional[str] = Unassigned()
+    data_cache_config: Optional[InferenceComponentDataCacheConfigSummary] = Unassigned()
 
 
 class InferenceComponentRuntimeConfigSummary(Base):
@@ -9356,6 +9797,27 @@ 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
@@ -9459,6 +9921,9 @@ 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.
@@ -9473,6 +9938,9 @@ 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()
@@ -9871,9 +10339,11 @@ 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.
+    ip_address_type: The IP address type for the domain. Specify ipv4 for IPv4-only connectivity or dualstack for both IPv4 and IPv6 connectivity. When you specify dualstack, the subnet must support IPv6 CIDR blocks.
     """
 
     r_studio_server_pro_domain_settings_for_update: Optional[
@@ -9881,9 +10351,13 @@ 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()
+    ip_address_type: Optional[str] = Unassigned()
 
 
 class PredefinedMetricSpecification(Base):
@@ -11925,6 +12399,7 @@ 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.
     """
@@ -11942,6 +12417,7 @@ 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()
 
@@ -12027,6 +12503,39 @@ 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
@@ -12746,6 +13255,9 @@ 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.
@@ -12757,6 +13269,9 @@ 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()