aws-sdk-sagemaker 1.339.0 → 1.340.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f99f676fe2b17eb076e8761bee93ce0bfaee796c41dc984e1eab0803c1947f2e
-  data.tar.gz: 6b3644ed5504af87e03d6b11d457c9cfa1bcf428b917150a2bad9a661968f654
+  metadata.gz: f760b6f6d6902ca08349489fe9e34c577365953a32aa2f031a4db9e67aa9cb08
+  data.tar.gz: 5d01231c9d2c1d978d56deee398fb98fe79da54085d362172671724d6bce3233
 SHA512:
-  metadata.gz: c26fc869f314ef2b25b1b2e0c58c9926c7b20b740a5f46064e31618cd4af601938f5df74199fce53c2c2d5494059acbec30b71727ae6534400013bbee5516433
-  data.tar.gz: 2bbffdc253a295bf9b9aa9fb1ae956ba268bb2d6d27abce4574ad0a4e0d1861c6ce0d84f655bbb45ed6959be27b34820b399c908c96e87de3b5d4c7dff93ed6b
+  metadata.gz: a658467635f982e5e53c0cd5a428c96d8f17acb120d16c31184b8ac8ddd2f21c9062c41e6df84610f95227118ae6de6a47053642188e8ed29208e2d44cfa5863
+  data.tar.gz: ec789fc4a9c2d3014b4e19c7a5b628f158fdc8a3b262139e86e44147b83a65107844ac19445d924aa41f1e90791d961c6c1bf8abb2ef19a9de49e6a54e63cba0

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.340.0 (2025-11-20)
+------------------
+
+* Feature - Added training plan support for inference endpoints. Added HyperPod task governance with accelerator partition-based quota allocation. Added BatchRebootClusterNodes and BatchReplaceClusterNodes APIs. Updated ListClusterNodes to include privateDnsHostName.
+
 1.339.0 (2025-11-19)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.339.0
+1.340.0

data/lib/aws-sdk-sagemaker/client.rb

@@ -950,6 +950,209 @@ module Aws::SageMaker
       req.send_request(options)
     end
 
+    # Reboots specific nodes within a SageMaker HyperPod cluster using a
+    # soft recovery mechanism. `BatchRebootClusterNodes` performs a graceful
+    # reboot of the specified nodes by calling the Amazon Elastic Compute
+    # Cloud `RebootInstances` API, which attempts to cleanly shut down the
+    # operating system before restarting the instance.
+    #
+    # This operation is useful for recovering from transient issues or
+    # applying certain configuration changes that require a restart.
+    #
+    # <note markdown="1"> * Rebooting a node may cause temporary service interruption for
+    #   workloads running on that node. Ensure your workloads can handle
+    #   node restarts or use appropriate scheduling to minimize impact.
+    #
+    # * You can reboot up to 25 nodes in a single request.
+    #
+    # * For SageMaker HyperPod clusters using the Slurm workload manager,
+    #   ensure rebooting nodes will not disrupt critical cluster operations.
+    #
+    #  </note>
+    #
+    # @option params [required, String] :cluster_name
+    #   The name or Amazon Resource Name (ARN) of the SageMaker HyperPod
+    #   cluster containing the nodes to reboot.
+    #
+    # @option params [Array<String>] :node_ids
+    #   A list of EC2 instance IDs to reboot using soft recovery. You can
+    #   specify between 1 and 25 instance IDs.
+    #
+    #   <note markdown="1"> * Either `NodeIds` or `NodeLogicalIds` must be provided (or both), but
+    #     at least one is required.
+    #
+    #   * Each instance ID must follow the pattern `i-` followed by 17
+    #     hexadecimal characters (for example, `i-0123456789abcdef0`).
+    #
+    #    </note>
+    #
+    # @option params [Array<String>] :node_logical_ids
+    #   A list of logical node IDs to reboot using soft recovery. You can
+    #   specify between 1 and 25 logical node IDs.
+    #
+    #   The `NodeLogicalId` is a unique identifier that persists throughout
+    #   the node's lifecycle and can be used to track nodes that are still
+    #   being provisioned and don't yet have an EC2 instance ID assigned.
+    #
+    #   * This parameter is only supported for clusters using `Continuous` as
+    #     the `NodeProvisioningMode`. For clusters using the default
+    #     provisioning mode, use `NodeIds` instead.
+    #
+    #   * Either `NodeIds` or `NodeLogicalIds` must be provided (or both), but
+    #     at least one is required.
+    #
+    # @return [Types::BatchRebootClusterNodesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
+    #
+    #   * {Types::BatchRebootClusterNodesResponse#successful #successful} => Array&lt;String&gt;
+    #   * {Types::BatchRebootClusterNodesResponse#failed #failed} => Array&lt;Types::BatchRebootClusterNodesError&gt;
+    #   * {Types::BatchRebootClusterNodesResponse#failed_node_logical_ids #failed_node_logical_ids} => Array&lt;Types::BatchRebootClusterNodeLogicalIdsError&gt;
+    #   * {Types::BatchRebootClusterNodesResponse#successful_node_logical_ids #successful_node_logical_ids} => Array&lt;String&gt;
+    #
+    # @example Request syntax with placeholder values
+    #
+    #   resp = client.batch_reboot_cluster_nodes({
+    #     cluster_name: "ClusterNameOrArn", # required
+    #     node_ids: ["ClusterNodeId"],
+    #     node_logical_ids: ["ClusterNodeLogicalId"],
+    #   })
+    #
+    # @example Response structure
+    #
+    #   resp.successful #=> Array
+    #   resp.successful[0] #=> String
+    #   resp.failed #=> Array
+    #   resp.failed[0].node_id #=> String
+    #   resp.failed[0].error_code #=> String, one of "InstanceIdNotFound", "InvalidInstanceStatus", "InstanceIdInUse", "InternalServerError"
+    #   resp.failed[0].message #=> String
+    #   resp.failed_node_logical_ids #=> Array
+    #   resp.failed_node_logical_ids[0].node_logical_id #=> String
+    #   resp.failed_node_logical_ids[0].error_code #=> String, one of "InstanceIdNotFound", "InvalidInstanceStatus", "InstanceIdInUse", "InternalServerError"
+    #   resp.failed_node_logical_ids[0].message #=> String
+    #   resp.successful_node_logical_ids #=> Array
+    #   resp.successful_node_logical_ids[0] #=> String
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchRebootClusterNodes AWS API Documentation
+    #
+    # @overload batch_reboot_cluster_nodes(params = {})
+    # @param [Hash] params ({})
+    def batch_reboot_cluster_nodes(params = {}, options = {})
+      req = build_request(:batch_reboot_cluster_nodes, params)
+      req.send_request(options)
+    end
+
+    # Replaces specific nodes within a SageMaker HyperPod cluster with new
+    # hardware. `BatchReplaceClusterNodes` terminates the specified
+    # instances and provisions new replacement instances with the same
+    # configuration but fresh hardware. The Amazon Machine Image (AMI) and
+    # instance configuration remain the same.
+    #
+    # This operation is useful for recovering from hardware failures or
+    # persistent issues that cannot be resolved through a reboot.
+    #
+    # * **Data Loss Warning:** Replacing nodes destroys all instance
+    #   volumes, including both root and secondary volumes. All data stored
+    #   on these volumes will be permanently lost and cannot be recovered.
+    #
+    # * To safeguard your work, back up your data to Amazon S3 or an FSx for
+    #   Lustre file system before invoking the API on a worker node group.
+    #   This will help prevent any potential data loss from the instance
+    #   root volume. For more information about backup, see [Use the backup
+    #   script provided by SageMaker HyperPod][1].
+    #
+    # * If you want to invoke this API on an existing cluster, you'll first
+    #   need to patch the cluster by running the [UpdateClusterSoftware
+    #   API][2]. For more information about patching a cluster, see [Update
+    #   the SageMaker HyperPod platform software of a cluster][3].
+    #
+    # * You can replace up to 25 nodes in a single request.
+    #
+    #
+    #
+    # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-operate-cli-command.html#sagemaker-hyperpod-operate-cli-command-update-cluster-software-backup
+    # [2]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_UpdateClusterSoftware.html
+    # [3]: https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-operate-cli-command.html#sagemaker-hyperpod-operate-cli-command-update-cluster-software
+    #
+    # @option params [required, String] :cluster_name
+    #   The name or Amazon Resource Name (ARN) of the SageMaker HyperPod
+    #   cluster containing the nodes to replace.
+    #
+    # @option params [Array<String>] :node_ids
+    #   A list of EC2 instance IDs to replace with new hardware. You can
+    #   specify between 1 and 25 instance IDs.
+    #
+    #   Replace operations destroy all instance volumes (root and secondary).
+    #   Ensure you have backed up any important data before proceeding.
+    #
+    #   <note markdown="1"> * Either `NodeIds` or `NodeLogicalIds` must be provided (or both), but
+    #     at least one is required.
+    #
+    #   * Each instance ID must follow the pattern `i-` followed by 17
+    #     hexadecimal characters (for example, `i-0123456789abcdef0`).
+    #
+    #   * For SageMaker HyperPod clusters using the Slurm workload manager,
+    #     you cannot replace instances that are configured as Slurm controller
+    #     nodes.
+    #
+    #    </note>
+    #
+    # @option params [Array<String>] :node_logical_ids
+    #   A list of logical node IDs to replace with new hardware. You can
+    #   specify between 1 and 25 logical node IDs.
+    #
+    #   The `NodeLogicalId` is a unique identifier that persists throughout
+    #   the node's lifecycle and can be used to track nodes that are still
+    #   being provisioned and don't yet have an EC2 instance ID assigned.
+    #
+    #   * Replace operations destroy all instance volumes (root and
+    #     secondary). Ensure you have backed up any important data before
+    #     proceeding.
+    #
+    #   * This parameter is only supported for clusters using `Continuous` as
+    #     the `NodeProvisioningMode`. For clusters using the default
+    #     provisioning mode, use `NodeIds` instead.
+    #
+    #   * Either `NodeIds` or `NodeLogicalIds` must be provided (or both), but
+    #     at least one is required.
+    #
+    # @return [Types::BatchReplaceClusterNodesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
+    #
+    #   * {Types::BatchReplaceClusterNodesResponse#successful #successful} => Array&lt;String&gt;
+    #   * {Types::BatchReplaceClusterNodesResponse#failed #failed} => Array&lt;Types::BatchReplaceClusterNodesError&gt;
+    #   * {Types::BatchReplaceClusterNodesResponse#failed_node_logical_ids #failed_node_logical_ids} => Array&lt;Types::BatchReplaceClusterNodeLogicalIdsError&gt;
+    #   * {Types::BatchReplaceClusterNodesResponse#successful_node_logical_ids #successful_node_logical_ids} => Array&lt;String&gt;
+    #
+    # @example Request syntax with placeholder values
+    #
+    #   resp = client.batch_replace_cluster_nodes({
+    #     cluster_name: "ClusterNameOrArn", # required
+    #     node_ids: ["ClusterNodeId"],
+    #     node_logical_ids: ["ClusterNodeLogicalId"],
+    #   })
+    #
+    # @example Response structure
+    #
+    #   resp.successful #=> Array
+    #   resp.successful[0] #=> String
+    #   resp.failed #=> Array
+    #   resp.failed[0].node_id #=> String
+    #   resp.failed[0].error_code #=> String, one of "InstanceIdNotFound", "InvalidInstanceStatus", "InstanceIdInUse", "InternalServerError"
+    #   resp.failed[0].message #=> String
+    #   resp.failed_node_logical_ids #=> Array
+    #   resp.failed_node_logical_ids[0].node_logical_id #=> String
+    #   resp.failed_node_logical_ids[0].error_code #=> String, one of "InstanceIdNotFound", "InvalidInstanceStatus", "InstanceIdInUse", "InternalServerError"
+    #   resp.failed_node_logical_ids[0].message #=> String
+    #   resp.successful_node_logical_ids #=> Array
+    #   resp.successful_node_logical_ids[0] #=> String
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchReplaceClusterNodes AWS API Documentation
+    #
+    # @overload batch_replace_cluster_nodes(params = {})
+    # @param [Hash] params ({})
+    def batch_replace_cluster_nodes(params = {}, options = {})
+      req = build_request(:batch_replace_cluster_nodes, params)
+      req.send_request(options)
+    end
+
     # Creates an *action*. An action is a lineage tracking entity that
     # represents an action or activity. For example, a model deployment or
     # an HPO job. Generally, an action involves at least one input or output
@@ -2725,6 +2928,10 @@ module Aws::SageMaker
     #           accelerators: 1,
     #           v_cpu: 1.0,
     #           memory_in_gi_b: 1.0,
+    #           accelerator_partition: {
+    #             type: "mig-1g.5gb", # required, accepts mig-1g.5gb, mig-1g.10gb, mig-1g.18gb, mig-1g.20gb, mig-1g.23gb, mig-1g.35gb, mig-1g.45gb, mig-1g.47gb, mig-2g.10gb, mig-2g.20gb, mig-2g.35gb, mig-2g.45gb, mig-2g.47gb, mig-3g.20gb, mig-3g.40gb, mig-3g.71gb, mig-3g.90gb, mig-3g.93gb, mig-4g.20gb, mig-4g.40gb, mig-4g.71gb, mig-4g.90gb, mig-4g.93gb, mig-7g.40gb, mig-7g.80gb, mig-7g.141gb, mig-7g.180gb, mig-7g.186gb
+    #             count: 1, # required
+    #           },
     #         },
     #       ],
     #       resource_sharing_config: {
@@ -13912,6 +14119,8 @@ module Aws::SageMaker
     #   resp.compute_quota_config.compute_quota_resources[0].accelerators #=> Integer
     #   resp.compute_quota_config.compute_quota_resources[0].v_cpu #=> Float
     #   resp.compute_quota_config.compute_quota_resources[0].memory_in_gi_b #=> Float
+    #   resp.compute_quota_config.compute_quota_resources[0].accelerator_partition.type #=> String, one of "mig-1g.5gb", "mig-1g.10gb", "mig-1g.18gb", "mig-1g.20gb", "mig-1g.23gb", "mig-1g.35gb", "mig-1g.45gb", "mig-1g.47gb", "mig-2g.10gb", "mig-2g.20gb", "mig-2g.35gb", "mig-2g.45gb", "mig-2g.47gb", "mig-3g.20gb", "mig-3g.40gb", "mig-3g.71gb", "mig-3g.90gb", "mig-3g.93gb", "mig-4g.20gb", "mig-4g.40gb", "mig-4g.71gb", "mig-4g.90gb", "mig-4g.93gb", "mig-7g.40gb", "mig-7g.80gb", "mig-7g.141gb", "mig-7g.180gb", "mig-7g.186gb"
+    #   resp.compute_quota_config.compute_quota_resources[0].accelerator_partition.count #=> Integer
     #   resp.compute_quota_config.resource_sharing_config.strategy #=> String, one of "Lend", "DontLend", "LendAndBorrow"
     #   resp.compute_quota_config.resource_sharing_config.borrow_limit #=> Integer
     #   resp.compute_quota_config.preempt_team_tasks #=> String, one of "Never", "LowerPriority"
@@ -18411,7 +18620,7 @@ module Aws::SageMaker
     #   resp.available_spare_instance_count #=> Integer
     #   resp.total_ultra_server_count #=> Integer
     #   resp.target_resources #=> Array
-    #   resp.target_resources[0] #=> String, one of "training-job", "hyperpod-cluster"
+    #   resp.target_resources[0] #=> String, one of "training-job", "hyperpod-cluster", "endpoint"
     #   resp.reserved_capacity_summaries #=> Array
     #   resp.reserved_capacity_summaries[0].reserved_capacity_arn #=> String
     #   resp.reserved_capacity_summaries[0].reserved_capacity_type #=> String, one of "UltraServer", "Instance"
@@ -20350,6 +20559,7 @@ module Aws::SageMaker
     #   resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound"
     #   resp.cluster_node_summaries[0].instance_status.message #=> String
     #   resp.cluster_node_summaries[0].ultra_server_info.id #=> String
+    #   resp.cluster_node_summaries[0].private_dns_hostname #=> String
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterNodes AWS API Documentation
     #
@@ -20813,6 +21023,8 @@ module Aws::SageMaker
     #   resp.compute_quota_summaries[0].compute_quota_config.compute_quota_resources[0].accelerators #=> Integer
     #   resp.compute_quota_summaries[0].compute_quota_config.compute_quota_resources[0].v_cpu #=> Float
     #   resp.compute_quota_summaries[0].compute_quota_config.compute_quota_resources[0].memory_in_gi_b #=> Float
+    #   resp.compute_quota_summaries[0].compute_quota_config.compute_quota_resources[0].accelerator_partition.type #=> String, one of "mig-1g.5gb", "mig-1g.10gb", "mig-1g.18gb", "mig-1g.20gb", "mig-1g.23gb", "mig-1g.35gb", "mig-1g.45gb", "mig-1g.47gb", "mig-2g.10gb", "mig-2g.20gb", "mig-2g.35gb", "mig-2g.45gb", "mig-2g.47gb", "mig-3g.20gb", "mig-3g.40gb", "mig-3g.71gb", "mig-3g.90gb", "mig-3g.93gb", "mig-4g.20gb", "mig-4g.40gb", "mig-4g.71gb", "mig-4g.90gb", "mig-4g.93gb", "mig-7g.40gb", "mig-7g.80gb", "mig-7g.141gb", "mig-7g.180gb", "mig-7g.186gb"
+    #   resp.compute_quota_summaries[0].compute_quota_config.compute_quota_resources[0].accelerator_partition.count #=> Integer
     #   resp.compute_quota_summaries[0].compute_quota_config.resource_sharing_config.strategy #=> String, one of "Lend", "DontLend", "LendAndBorrow"
     #   resp.compute_quota_summaries[0].compute_quota_config.resource_sharing_config.borrow_limit #=> Integer
     #   resp.compute_quota_summaries[0].compute_quota_config.preempt_team_tasks #=> String, one of "Never", "LowerPriority"
@@ -25460,7 +25672,7 @@ module Aws::SageMaker
     #   resp.training_plan_summaries[0].in_use_instance_count #=> Integer
     #   resp.training_plan_summaries[0].total_ultra_server_count #=> Integer
     #   resp.training_plan_summaries[0].target_resources #=> Array
-    #   resp.training_plan_summaries[0].target_resources[0] #=> String, one of "training-job", "hyperpod-cluster"
+    #   resp.training_plan_summaries[0].target_resources[0] #=> String, one of "training-job", "hyperpod-cluster", "endpoint"
     #   resp.training_plan_summaries[0].reserved_capacity_summaries #=> Array
     #   resp.training_plan_summaries[0].reserved_capacity_summaries[0].reserved_capacity_arn #=> String
     #   resp.training_plan_summaries[0].reserved_capacity_summaries[0].reserved_capacity_type #=> String, one of "UltraServer", "Instance"
@@ -26481,7 +26693,7 @@ module Aws::SageMaker
     #
     # @option params [required, Array<String>] :target_resources
     #   The target resources (e.g., SageMaker Training Jobs, SageMaker
-    #   HyperPod) to search for in the offerings.
+    #   HyperPod, SageMaker Endpoints) to search for in the offerings.
     #
     #   Training plans are specific to their target resource.
     #
@@ -26491,6 +26703,10 @@ module Aws::SageMaker
     #   * A training plan for HyperPod clusters can be used exclusively to
     #     provide compute resources to a cluster's instance group.
     #
+    #   * A training plan for SageMaker endpoints can be used exclusively to
+    #     provide compute resources to SageMaker endpoints for model
+    #     deployment.
+    #
     # @return [Types::SearchTrainingPlanOfferingsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
     #
     #   * {Types::SearchTrainingPlanOfferingsResponse#training_plan_offerings #training_plan_offerings} => Array&lt;Types::TrainingPlanOffering&gt;
@@ -26505,7 +26721,7 @@ module Aws::SageMaker
     #     start_time_after: Time.now,
     #     end_time_before: Time.now,
     #     duration_hours: 1, # required
-    #     target_resources: ["training-job"], # required, accepts training-job, hyperpod-cluster
+    #     target_resources: ["training-job"], # required, accepts training-job, hyperpod-cluster, endpoint
     #   })
     #
     # @example Response structure
@@ -26513,7 +26729,7 @@ module Aws::SageMaker
     #   resp.training_plan_offerings #=> Array
     #   resp.training_plan_offerings[0].training_plan_offering_id #=> String
     #   resp.training_plan_offerings[0].target_resources #=> Array
-    #   resp.training_plan_offerings[0].target_resources[0] #=> String, one of "training-job", "hyperpod-cluster"
+    #   resp.training_plan_offerings[0].target_resources[0] #=> String, one of "training-job", "hyperpod-cluster", "endpoint"
     #   resp.training_plan_offerings[0].requested_start_time_after #=> Time
     #   resp.training_plan_offerings[0].requested_end_time_before #=> Time
     #   resp.training_plan_offerings[0].duration_hours #=> Integer
@@ -27951,6 +28167,10 @@ module Aws::SageMaker
     #           accelerators: 1,
     #           v_cpu: 1.0,
     #           memory_in_gi_b: 1.0,
+    #           accelerator_partition: {
+    #             type: "mig-1g.5gb", # required, accepts mig-1g.5gb, mig-1g.10gb, mig-1g.18gb, mig-1g.20gb, mig-1g.23gb, mig-1g.35gb, mig-1g.45gb, mig-1g.47gb, mig-2g.10gb, mig-2g.20gb, mig-2g.35gb, mig-2g.45gb, mig-2g.47gb, mig-3g.20gb, mig-3g.40gb, mig-3g.71gb, mig-3g.90gb, mig-3g.93gb, mig-4g.20gb, mig-4g.40gb, mig-4g.71gb, mig-4g.90gb, mig-4g.93gb, mig-7g.40gb, mig-7g.80gb, mig-7g.141gb, mig-7g.180gb, mig-7g.186gb
+    #             count: 1, # required
+    #           },
     #         },
     #       ],
     #       resource_sharing_config: {
@@ -31359,7 +31579,7 @@ module Aws::SageMaker
         tracer: tracer
       )
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.339.0'
+      context[:gem_version] = '1.340.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemaker/client_api.rb

@@ -14,6 +14,8 @@ module Aws::SageMaker
 
     include Seahorse::Model
 
+    AcceleratorPartitionConfig = Shapes::StructureShape.new(name: 'AcceleratorPartitionConfig')
+    AcceleratorPartitionConfigCountInteger = Shapes::IntegerShape.new(name: 'AcceleratorPartitionConfigCountInteger')
     AcceleratorsAmount = Shapes::IntegerShape.new(name: 'AcceleratorsAmount')
     Accept = Shapes::StringShape.new(name: 'Accept')
     AcceptEula = Shapes::BooleanShape.new(name: 'AcceptEula')
@@ -211,6 +213,24 @@ module Aws::SageMaker
     BatchDescribeModelPackageInput = Shapes::StructureShape.new(name: 'BatchDescribeModelPackageInput')
     BatchDescribeModelPackageOutput = Shapes::StructureShape.new(name: 'BatchDescribeModelPackageOutput')
     BatchDescribeModelPackageSummary = Shapes::StructureShape.new(name: 'BatchDescribeModelPackageSummary')
+    BatchRebootClusterNodeLogicalIdsError = Shapes::StructureShape.new(name: 'BatchRebootClusterNodeLogicalIdsError')
+    BatchRebootClusterNodeLogicalIdsErrors = Shapes::ListShape.new(name: 'BatchRebootClusterNodeLogicalIdsErrors')
+    BatchRebootClusterNodesError = Shapes::StructureShape.new(name: 'BatchRebootClusterNodesError')
+    BatchRebootClusterNodesErrorCode = Shapes::StringShape.new(name: 'BatchRebootClusterNodesErrorCode')
+    BatchRebootClusterNodesErrors = Shapes::ListShape.new(name: 'BatchRebootClusterNodesErrors')
+    BatchRebootClusterNodesRequest = Shapes::StructureShape.new(name: 'BatchRebootClusterNodesRequest')
+    BatchRebootClusterNodesRequestNodeIdsList = Shapes::ListShape.new(name: 'BatchRebootClusterNodesRequestNodeIdsList')
+    BatchRebootClusterNodesRequestNodeLogicalIdsList = Shapes::ListShape.new(name: 'BatchRebootClusterNodesRequestNodeLogicalIdsList')
+    BatchRebootClusterNodesResponse = Shapes::StructureShape.new(name: 'BatchRebootClusterNodesResponse')
+    BatchReplaceClusterNodeLogicalIdsError = Shapes::StructureShape.new(name: 'BatchReplaceClusterNodeLogicalIdsError')
+    BatchReplaceClusterNodeLogicalIdsErrors = Shapes::ListShape.new(name: 'BatchReplaceClusterNodeLogicalIdsErrors')
+    BatchReplaceClusterNodesError = Shapes::StructureShape.new(name: 'BatchReplaceClusterNodesError')
+    BatchReplaceClusterNodesErrorCode = Shapes::StringShape.new(name: 'BatchReplaceClusterNodesErrorCode')
+    BatchReplaceClusterNodesErrors = Shapes::ListShape.new(name: 'BatchReplaceClusterNodesErrors')
+    BatchReplaceClusterNodesRequest = Shapes::StructureShape.new(name: 'BatchReplaceClusterNodesRequest')
+    BatchReplaceClusterNodesRequestNodeIdsList = Shapes::ListShape.new(name: 'BatchReplaceClusterNodesRequestNodeIdsList')
+    BatchReplaceClusterNodesRequestNodeLogicalIdsList = Shapes::ListShape.new(name: 'BatchReplaceClusterNodesRequestNodeLogicalIdsList')
+    BatchReplaceClusterNodesResponse = Shapes::StructureShape.new(name: 'BatchReplaceClusterNodesResponse')
     BatchStrategy = Shapes::StringShape.new(name: 'BatchStrategy')
     BatchTransformInput = Shapes::StructureShape.new(name: 'BatchTransformInput')
     BestObjectiveNotImproving = Shapes::StructureShape.new(name: 'BestObjectiveNotImproving')
@@ -1569,6 +1589,7 @@ module Aws::SageMaker
     LocalPath = Shapes::StringShape.new(name: 'LocalPath')
     Long = Shapes::IntegerShape.new(name: 'Long')
     LongS3Uri = Shapes::StringShape.new(name: 'LongS3Uri')
+    MIGProfileType = Shapes::StringShape.new(name: 'MIGProfileType')
     MLFramework = Shapes::StringShape.new(name: 'MLFramework')
     MajorMinorVersion = Shapes::StringShape.new(name: 'MajorMinorVersion')
     ManagedInstanceScalingMaxInstanceCount = Shapes::IntegerShape.new(name: 'ManagedInstanceScalingMaxInstanceCount')
@@ -2708,6 +2729,10 @@ module Aws::SageMaker
     WorkteamName = Shapes::StringShape.new(name: 'WorkteamName')
     Workteams = Shapes::ListShape.new(name: 'Workteams')
 
+    AcceleratorPartitionConfig.add_member(:type, Shapes::ShapeRef.new(shape: MIGProfileType, required: true, location_name: "Type"))
+    AcceleratorPartitionConfig.add_member(:count, Shapes::ShapeRef.new(shape: AcceleratorPartitionConfigCountInteger, required: true, location_name: "Count", metadata: {"box" => true}))
+    AcceleratorPartitionConfig.struct_class = Types::AcceleratorPartitionConfig
+
     ActionSource.add_member(:source_uri, Shapes::ShapeRef.new(shape: SourceUri, required: true, location_name: "SourceUri"))
     ActionSource.add_member(:source_type, Shapes::ShapeRef.new(shape: String256, location_name: "SourceType"))
     ActionSource.add_member(:source_id, Shapes::ShapeRef.new(shape: String256, location_name: "SourceId"))
@@ -3210,6 +3235,64 @@ module Aws::SageMaker
     BatchDescribeModelPackageSummary.add_member(:model_approval_status, Shapes::ShapeRef.new(shape: ModelApprovalStatus, location_name: "ModelApprovalStatus"))
     BatchDescribeModelPackageSummary.struct_class = Types::BatchDescribeModelPackageSummary
 
+    BatchRebootClusterNodeLogicalIdsError.add_member(:node_logical_id, Shapes::ShapeRef.new(shape: ClusterNodeLogicalId, required: true, location_name: "NodeLogicalId"))
+    BatchRebootClusterNodeLogicalIdsError.add_member(:error_code, Shapes::ShapeRef.new(shape: BatchRebootClusterNodesErrorCode, required: true, location_name: "ErrorCode"))
+    BatchRebootClusterNodeLogicalIdsError.add_member(:message, Shapes::ShapeRef.new(shape: String, required: true, location_name: "Message"))
+    BatchRebootClusterNodeLogicalIdsError.struct_class = Types::BatchRebootClusterNodeLogicalIdsError
+
+    BatchRebootClusterNodeLogicalIdsErrors.member = Shapes::ShapeRef.new(shape: BatchRebootClusterNodeLogicalIdsError)
+
+    BatchRebootClusterNodesError.add_member(:node_id, Shapes::ShapeRef.new(shape: ClusterNodeId, required: true, location_name: "NodeId"))
+    BatchRebootClusterNodesError.add_member(:error_code, Shapes::ShapeRef.new(shape: BatchRebootClusterNodesErrorCode, required: true, location_name: "ErrorCode"))
+    BatchRebootClusterNodesError.add_member(:message, Shapes::ShapeRef.new(shape: String, required: true, location_name: "Message"))
+    BatchRebootClusterNodesError.struct_class = Types::BatchRebootClusterNodesError
+
+    BatchRebootClusterNodesErrors.member = Shapes::ShapeRef.new(shape: BatchRebootClusterNodesError)
+
+    BatchRebootClusterNodesRequest.add_member(:cluster_name, Shapes::ShapeRef.new(shape: ClusterNameOrArn, required: true, location_name: "ClusterName"))
+    BatchRebootClusterNodesRequest.add_member(:node_ids, Shapes::ShapeRef.new(shape: BatchRebootClusterNodesRequestNodeIdsList, location_name: "NodeIds"))
+    BatchRebootClusterNodesRequest.add_member(:node_logical_ids, Shapes::ShapeRef.new(shape: BatchRebootClusterNodesRequestNodeLogicalIdsList, location_name: "NodeLogicalIds"))
+    BatchRebootClusterNodesRequest.struct_class = Types::BatchRebootClusterNodesRequest
+
+    BatchRebootClusterNodesRequestNodeIdsList.member = Shapes::ShapeRef.new(shape: ClusterNodeId)
+
+    BatchRebootClusterNodesRequestNodeLogicalIdsList.member = Shapes::ShapeRef.new(shape: ClusterNodeLogicalId)
+
+    BatchRebootClusterNodesResponse.add_member(:successful, Shapes::ShapeRef.new(shape: ClusterNodeIds, location_name: "Successful"))
+    BatchRebootClusterNodesResponse.add_member(:failed, Shapes::ShapeRef.new(shape: BatchRebootClusterNodesErrors, location_name: "Failed"))
+    BatchRebootClusterNodesResponse.add_member(:failed_node_logical_ids, Shapes::ShapeRef.new(shape: BatchRebootClusterNodeLogicalIdsErrors, location_name: "FailedNodeLogicalIds"))
+    BatchRebootClusterNodesResponse.add_member(:successful_node_logical_ids, Shapes::ShapeRef.new(shape: ClusterNodeLogicalIdList, location_name: "SuccessfulNodeLogicalIds"))
+    BatchRebootClusterNodesResponse.struct_class = Types::BatchRebootClusterNodesResponse
+
+    BatchReplaceClusterNodeLogicalIdsError.add_member(:node_logical_id, Shapes::ShapeRef.new(shape: ClusterNodeLogicalId, required: true, location_name: "NodeLogicalId"))
+    BatchReplaceClusterNodeLogicalIdsError.add_member(:error_code, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesErrorCode, required: true, location_name: "ErrorCode"))
+    BatchReplaceClusterNodeLogicalIdsError.add_member(:message, Shapes::ShapeRef.new(shape: String, required: true, location_name: "Message"))
+    BatchReplaceClusterNodeLogicalIdsError.struct_class = Types::BatchReplaceClusterNodeLogicalIdsError
+
+    BatchReplaceClusterNodeLogicalIdsErrors.member = Shapes::ShapeRef.new(shape: BatchReplaceClusterNodeLogicalIdsError)
+
+    BatchReplaceClusterNodesError.add_member(:node_id, Shapes::ShapeRef.new(shape: ClusterNodeId, required: true, location_name: "NodeId"))
+    BatchReplaceClusterNodesError.add_member(:error_code, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesErrorCode, required: true, location_name: "ErrorCode"))
+    BatchReplaceClusterNodesError.add_member(:message, Shapes::ShapeRef.new(shape: String, required: true, location_name: "Message"))
+    BatchReplaceClusterNodesError.struct_class = Types::BatchReplaceClusterNodesError
+
+    BatchReplaceClusterNodesErrors.member = Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesError)
+
+    BatchReplaceClusterNodesRequest.add_member(:cluster_name, Shapes::ShapeRef.new(shape: ClusterNameOrArn, required: true, location_name: "ClusterName"))
+    BatchReplaceClusterNodesRequest.add_member(:node_ids, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesRequestNodeIdsList, location_name: "NodeIds"))
+    BatchReplaceClusterNodesRequest.add_member(:node_logical_ids, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesRequestNodeLogicalIdsList, location_name: "NodeLogicalIds"))
+    BatchReplaceClusterNodesRequest.struct_class = Types::BatchReplaceClusterNodesRequest
+
+    BatchReplaceClusterNodesRequestNodeIdsList.member = Shapes::ShapeRef.new(shape: ClusterNodeId)
+
+    BatchReplaceClusterNodesRequestNodeLogicalIdsList.member = Shapes::ShapeRef.new(shape: ClusterNodeLogicalId)
+
+    BatchReplaceClusterNodesResponse.add_member(:successful, Shapes::ShapeRef.new(shape: ClusterNodeIds, location_name: "Successful"))
+    BatchReplaceClusterNodesResponse.add_member(:failed, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesErrors, location_name: "Failed"))
+    BatchReplaceClusterNodesResponse.add_member(:failed_node_logical_ids, Shapes::ShapeRef.new(shape: BatchReplaceClusterNodeLogicalIdsErrors, location_name: "FailedNodeLogicalIds"))
+    BatchReplaceClusterNodesResponse.add_member(:successful_node_logical_ids, Shapes::ShapeRef.new(shape: ClusterNodeLogicalIdList, location_name: "SuccessfulNodeLogicalIds"))
+    BatchReplaceClusterNodesResponse.struct_class = Types::BatchReplaceClusterNodesResponse
+
     BatchTransformInput.add_member(:data_captured_destination_s3_uri, Shapes::ShapeRef.new(shape: DestinationS3Uri, required: true, location_name: "DataCapturedDestinationS3Uri"))
     BatchTransformInput.add_member(:dataset_format, Shapes::ShapeRef.new(shape: MonitoringDatasetFormat, required: true, location_name: "DatasetFormat"))
     BatchTransformInput.add_member(:local_path, Shapes::ShapeRef.new(shape: ProcessingLocalPath, required: true, location_name: "LocalPath"))
@@ -3561,6 +3644,7 @@ module Aws::SageMaker
     ClusterNodeSummary.add_member(:last_software_update_time, Shapes::ShapeRef.new(shape: Timestamp, location_name: "LastSoftwareUpdateTime"))
     ClusterNodeSummary.add_member(:instance_status, Shapes::ShapeRef.new(shape: ClusterInstanceStatusDetails, required: true, location_name: "InstanceStatus"))
     ClusterNodeSummary.add_member(:ultra_server_info, Shapes::ShapeRef.new(shape: UltraServerInfo, location_name: "UltraServerInfo"))
+    ClusterNodeSummary.add_member(:private_dns_hostname, Shapes::ShapeRef.new(shape: ClusterPrivateDnsHostname, location_name: "PrivateDnsHostname"))
     ClusterNodeSummary.struct_class = Types::ClusterNodeSummary
 
     ClusterOrchestrator.add_member(:eks, Shapes::ShapeRef.new(shape: ClusterOrchestratorEksConfig, required: true, location_name: "Eks"))
@@ -3703,6 +3787,7 @@ module Aws::SageMaker
     ComputeQuotaResourceConfig.add_member(:accelerators, Shapes::ShapeRef.new(shape: AcceleratorsAmount, location_name: "Accelerators"))
     ComputeQuotaResourceConfig.add_member(:v_cpu, Shapes::ShapeRef.new(shape: VCpuAmount, location_name: "VCpu"))
     ComputeQuotaResourceConfig.add_member(:memory_in_gi_b, Shapes::ShapeRef.new(shape: MemoryInGiBAmount, location_name: "MemoryInGiB"))
+    ComputeQuotaResourceConfig.add_member(:accelerator_partition, Shapes::ShapeRef.new(shape: AcceleratorPartitionConfig, location_name: "AcceleratorPartition"))
     ComputeQuotaResourceConfig.struct_class = Types::ComputeQuotaResourceConfig
 
     ComputeQuotaResourceConfigList.member = Shapes::ShapeRef.new(shape: ComputeQuotaResourceConfig)
@@ -12019,6 +12104,24 @@ module Aws::SageMaker
         o.output = Shapes::ShapeRef.new(shape: BatchDescribeModelPackageOutput)
       end)
 
+      api.add_operation(:batch_reboot_cluster_nodes, Seahorse::Model::Operation.new.tap do |o|
+        o.name = "BatchRebootClusterNodes"
+        o.http_method = "POST"
+        o.http_request_uri = "/"
+        o.input = Shapes::ShapeRef.new(shape: BatchRebootClusterNodesRequest)
+        o.output = Shapes::ShapeRef.new(shape: BatchRebootClusterNodesResponse)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceNotFound)
+      end)
+
+      api.add_operation(:batch_replace_cluster_nodes, Seahorse::Model::Operation.new.tap do |o|
+        o.name = "BatchReplaceClusterNodes"
+        o.http_method = "POST"
+        o.http_request_uri = "/"
+        o.input = Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesRequest)
+        o.output = Shapes::ShapeRef.new(shape: BatchReplaceClusterNodesResponse)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceNotFound)
+      end)
+
       api.add_operation(:create_action, Seahorse::Model::Operation.new.tap do |o|
         o.name = "CreateAction"
         o.http_method = "POST"

data/lib/aws-sdk-sagemaker/types.rb

@@ -10,6 +10,33 @@
 module Aws::SageMaker
   module Types
 
+    # Configuration for allocating accelerator partitions.
+    #
+    # @!attribute [rw] type
+    #   The Multi-Instance GPU (MIG) profile type that defines the partition
+    #   configuration. The profile specifies the compute and memory
+    #   allocation for each partition instance. The available profile types
+    #   depend on the instance type specified in the compute quota
+    #   configuration.
+    #   @return [String]
+    #
+    # @!attribute [rw] count
+    #   The number of accelerator partitions to allocate with the specified
+    #   partition type. If you don't specify a value for vCPU and
+    #   MemoryInGiB, SageMaker AI automatically allocates ratio-based values
+    #   for those parameters based on the accelerator partition count you
+    #   provide.
+    #   @return [Integer]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AcceleratorPartitionConfig AWS API Documentation
+    #
+    class AcceleratorPartitionConfig < Struct.new(
+      :type,
+      :count)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # A structure describing the source of an action.
     #
     # @!attribute [rw] source_uri
@@ -3452,6 +3479,348 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
+    # Represents an error encountered when rebooting a node (identified by
+    # its logical node ID) from a SageMaker HyperPod cluster.
+    #
+    # @!attribute [rw] node_logical_id
+    #   The logical node ID of the node that encountered an error during the
+    #   reboot operation.
+    #   @return [String]
+    #
+    # @!attribute [rw] error_code
+    #   The error code associated with the error encountered when rebooting
+    #   a node by logical node ID.
+    #
+    #   Possible values:
+    #
+    #   * `InstanceIdNotFound`: The node does not exist in the specified
+    #     cluster.
+    #
+    #   * `InvalidInstanceStatus`: The node is in a state that does not
+    #     allow rebooting. Wait for the node to finish any ongoing changes
+    #     before retrying.
+    #
+    #   * `InstanceIdInUse`: Another operation is already in progress for
+    #     this node. Wait for the operation to complete before retrying.
+    #
+    #   * `InternalServerError`: An internal error occurred while processing
+    #     this node.
+    #   @return [String]
+    #
+    # @!attribute [rw] message
+    #   A human-readable message describing the error encountered when
+    #   rebooting a node by logical node ID.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchRebootClusterNodeLogicalIdsError AWS API Documentation
+    #
+    class BatchRebootClusterNodeLogicalIdsError < Struct.new(
+      :node_logical_id,
+      :error_code,
+      :message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # Represents an error encountered when rebooting a node from a SageMaker
+    # HyperPod cluster.
+    #
+    # @!attribute [rw] node_id
+    #   The EC2 instance ID of the node that encountered an error during the
+    #   reboot operation.
+    #   @return [String]
+    #
+    # @!attribute [rw] error_code
+    #   The error code associated with the error encountered when rebooting
+    #   a node.
+    #
+    #   Possible values:
+    #
+    #   * `InstanceIdNotFound`: The instance does not exist in the specified
+    #     cluster.
+    #
+    #   * `InvalidInstanceStatus`: The instance is in a state that does not
+    #     allow rebooting. Wait for the instance to finish any ongoing
+    #     changes before retrying.
+    #
+    #   * `InstanceIdInUse`: Another operation is already in progress for
+    #     this node. Wait for the operation to complete before retrying.
+    #
+    #   * `InternalServerError`: An internal error occurred while processing
+    #     this node.
+    #   @return [String]
+    #
+    # @!attribute [rw] message
+    #   A human-readable message describing the error encountered when
+    #   rebooting a node.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchRebootClusterNodesError AWS API Documentation
+    #
+    class BatchRebootClusterNodesError < Struct.new(
+      :node_id,
+      :error_code,
+      :message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # @!attribute [rw] cluster_name
+    #   The name or Amazon Resource Name (ARN) of the SageMaker HyperPod
+    #   cluster containing the nodes to reboot.
+    #   @return [String]
+    #
+    # @!attribute [rw] node_ids
+    #   A list of EC2 instance IDs to reboot using soft recovery. You can
+    #   specify between 1 and 25 instance IDs.
+    #
+    #   <note markdown="1"> * Either `NodeIds` or `NodeLogicalIds` must be provided (or both),
+    #     but at least one is required.
+    #
+    #   * Each instance ID must follow the pattern `i-` followed by 17
+    #     hexadecimal characters (for example, `i-0123456789abcdef0`).
+    #
+    #    </note>
+    #   @return [Array<String>]
+    #
+    # @!attribute [rw] node_logical_ids
+    #   A list of logical node IDs to reboot using soft recovery. You can
+    #   specify between 1 and 25 logical node IDs.
+    #
+    #   The `NodeLogicalId` is a unique identifier that persists throughout
+    #   the node's lifecycle and can be used to track nodes that are still
+    #   being provisioned and don't yet have an EC2 instance ID assigned.
+    #
+    #   * This parameter is only supported for clusters using `Continuous`
+    #     as the `NodeProvisioningMode`. For clusters using the default
+    #     provisioning mode, use `NodeIds` instead.
+    #
+    #   * Either `NodeIds` or `NodeLogicalIds` must be provided (or both),
+    #     but at least one is required.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchRebootClusterNodesRequest AWS API Documentation
+    #
+    class BatchRebootClusterNodesRequest < Struct.new(
+      :cluster_name,
+      :node_ids,
+      :node_logical_ids)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # @!attribute [rw] successful
+    #   A list of EC2 instance IDs for which the reboot operation was
+    #   successfully initiated.
+    #   @return [Array<String>]
+    #
+    # @!attribute [rw] failed
+    #   A list of errors encountered for EC2 instance IDs that could not be
+    #   rebooted. Each error includes the instance ID, an error code, and a
+    #   descriptive message.
+    #   @return [Array<Types::BatchRebootClusterNodesError>]
+    #
+    # @!attribute [rw] failed_node_logical_ids
+    #   A list of errors encountered for logical node IDs that could not be
+    #   rebooted. Each error includes the logical node ID, an error code,
+    #   and a descriptive message. This field is only present when
+    #   `NodeLogicalIds` were provided in the request.
+    #   @return [Array<Types::BatchRebootClusterNodeLogicalIdsError>]
+    #
+    # @!attribute [rw] successful_node_logical_ids
+    #   A list of logical node IDs for which the reboot operation was
+    #   successfully initiated. This field is only present when
+    #   `NodeLogicalIds` were provided in the request.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchRebootClusterNodesResponse AWS API Documentation
+    #
+    class BatchRebootClusterNodesResponse < Struct.new(
+      :successful,
+      :failed,
+      :failed_node_logical_ids,
+      :successful_node_logical_ids)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # Represents an error encountered when replacing a node (identified by
+    # its logical node ID) in a SageMaker HyperPod cluster.
+    #
+    # @!attribute [rw] node_logical_id
+    #   The logical node ID of the node that encountered an error during the
+    #   replacement operation.
+    #   @return [String]
+    #
+    # @!attribute [rw] error_code
+    #   The error code associated with the error encountered when replacing
+    #   a node by logical node ID.
+    #
+    #   Possible values:
+    #
+    #   * `InstanceIdNotFound`: The node does not exist in the specified
+    #     cluster.
+    #
+    #   * `InvalidInstanceStatus`: The node is in a state that does not
+    #     allow replacement. Wait for the node to finish any ongoing changes
+    #     before retrying.
+    #
+    #   * `InstanceIdInUse`: Another operation is already in progress for
+    #     this node. Wait for the operation to complete before retrying.
+    #
+    #   * `InternalServerError`: An internal error occurred while processing
+    #     this node.
+    #   @return [String]
+    #
+    # @!attribute [rw] message
+    #   A human-readable message describing the error encountered when
+    #   replacing a node by logical node ID.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchReplaceClusterNodeLogicalIdsError AWS API Documentation
+    #
+    class BatchReplaceClusterNodeLogicalIdsError < Struct.new(
+      :node_logical_id,
+      :error_code,
+      :message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # Represents an error encountered when replacing a node in a SageMaker
+    # HyperPod cluster.
+    #
+    # @!attribute [rw] node_id
+    #   The EC2 instance ID of the node that encountered an error during the
+    #   replacement operation.
+    #   @return [String]
+    #
+    # @!attribute [rw] error_code
+    #   The error code associated with the error encountered when replacing
+    #   a node.
+    #
+    #   Possible values:
+    #
+    #   * `InstanceIdNotFound`: The instance does not exist in the specified
+    #     cluster.
+    #
+    #   * `InvalidInstanceStatus`: The instance is in a state that does not
+    #     allow replacement. Wait for the instance to finish any ongoing
+    #     changes before retrying.
+    #
+    #   * `InstanceIdInUse`: Another operation is already in progress for
+    #     this node. Wait for the operation to complete before retrying.
+    #
+    #   * `InternalServerError`: An internal error occurred while processing
+    #     this node.
+    #   @return [String]
+    #
+    # @!attribute [rw] message
+    #   A human-readable message describing the error encountered when
+    #   replacing a node.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchReplaceClusterNodesError AWS API Documentation
+    #
+    class BatchReplaceClusterNodesError < Struct.new(
+      :node_id,
+      :error_code,
+      :message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # @!attribute [rw] cluster_name
+    #   The name or Amazon Resource Name (ARN) of the SageMaker HyperPod
+    #   cluster containing the nodes to replace.
+    #   @return [String]
+    #
+    # @!attribute [rw] node_ids
+    #   A list of EC2 instance IDs to replace with new hardware. You can
+    #   specify between 1 and 25 instance IDs.
+    #
+    #   Replace operations destroy all instance volumes (root and
+    #   secondary). Ensure you have backed up any important data before
+    #   proceeding.
+    #
+    #   <note markdown="1"> * Either `NodeIds` or `NodeLogicalIds` must be provided (or both),
+    #     but at least one is required.
+    #
+    #   * Each instance ID must follow the pattern `i-` followed by 17
+    #     hexadecimal characters (for example, `i-0123456789abcdef0`).
+    #
+    #   * For SageMaker HyperPod clusters using the Slurm workload manager,
+    #     you cannot replace instances that are configured as Slurm
+    #     controller nodes.
+    #
+    #    </note>
+    #   @return [Array<String>]
+    #
+    # @!attribute [rw] node_logical_ids
+    #   A list of logical node IDs to replace with new hardware. You can
+    #   specify between 1 and 25 logical node IDs.
+    #
+    #   The `NodeLogicalId` is a unique identifier that persists throughout
+    #   the node's lifecycle and can be used to track nodes that are still
+    #   being provisioned and don't yet have an EC2 instance ID assigned.
+    #
+    #   * Replace operations destroy all instance volumes (root and
+    #     secondary). Ensure you have backed up any important data before
+    #     proceeding.
+    #
+    #   * This parameter is only supported for clusters using `Continuous`
+    #     as the `NodeProvisioningMode`. For clusters using the default
+    #     provisioning mode, use `NodeIds` instead.
+    #
+    #   * Either `NodeIds` or `NodeLogicalIds` must be provided (or both),
+    #     but at least one is required.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchReplaceClusterNodesRequest AWS API Documentation
+    #
+    class BatchReplaceClusterNodesRequest < Struct.new(
+      :cluster_name,
+      :node_ids,
+      :node_logical_ids)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # @!attribute [rw] successful
+    #   A list of EC2 instance IDs for which the replacement operation was
+    #   successfully initiated.
+    #   @return [Array<String>]
+    #
+    # @!attribute [rw] failed
+    #   A list of errors encountered for EC2 instance IDs that could not be
+    #   replaced. Each error includes the instance ID, an error code, and a
+    #   descriptive message.
+    #   @return [Array<Types::BatchReplaceClusterNodesError>]
+    #
+    # @!attribute [rw] failed_node_logical_ids
+    #   A list of errors encountered for logical node IDs that could not be
+    #   replaced. Each error includes the logical node ID, an error code,
+    #   and a descriptive message. This field is only present when
+    #   `NodeLogicalIds` were provided in the request.
+    #   @return [Array<Types::BatchReplaceClusterNodeLogicalIdsError>]
+    #
+    # @!attribute [rw] successful_node_logical_ids
+    #   A list of logical node IDs for which the replacement operation was
+    #   successfully initiated. This field is only present when
+    #   `NodeLogicalIds` were provided in the request.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/BatchReplaceClusterNodesResponse AWS API Documentation
+    #
+    class BatchReplaceClusterNodesResponse < Struct.new(
+      :successful,
+      :failed,
+      :failed_node_logical_ids,
+      :successful_node_logical_ids)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Input object for the batch transform job.
     #
     # @!attribute [rw] data_captured_destination_s3_uri
@@ -5536,6 +5905,10 @@ module Aws::SageMaker
     #   Contains information about the UltraServer.
     #   @return [Types::UltraServerInfo]
     #
+    # @!attribute [rw] private_dns_hostname
+    #   The private DNS hostname of the SageMaker HyperPod cluster node.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterNodeSummary AWS API Documentation
     #
     class ClusterNodeSummary < Struct.new(
@@ -5546,7 +5919,8 @@ module Aws::SageMaker
       :launch_time,
       :last_software_update_time,
       :instance_status,
-      :ultra_server_info)
+      :ultra_server_info,
+      :private_dns_hostname)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -6294,6 +6668,11 @@ module Aws::SageMaker
     #   Accelerators are set to 0.
     #   @return [Float]
     #
+    # @!attribute [rw] accelerator_partition
+    #   The accelerator partition configuration for fractional GPU
+    #   allocation.
+    #   @return [Types::AcceleratorPartitionConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ComputeQuotaResourceConfig AWS API Documentation
     #
     class ComputeQuotaResourceConfig < Struct.new(
@@ -6301,7 +6680,8 @@ module Aws::SageMaker
       :count,
       :accelerators,
       :v_cpu,
-      :memory_in_gi_b)
+      :memory_in_gi_b,
+      :accelerator_partition)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -20816,7 +21196,7 @@ module Aws::SageMaker
     #
     # @!attribute [rw] target_resources
     #   The target resources (e.g., SageMaker Training Jobs, SageMaker
-    #   HyperPod) that can use this training plan.
+    #   HyperPod, SageMaker Endpoints) that can use this training plan.
     #
     #   Training plans are specific to their target resource.
     #
@@ -20825,6 +21205,10 @@ module Aws::SageMaker
     #
     #   * A training plan for HyperPod clusters can be used exclusively to
     #     provide compute resources to a cluster's instance group.
+    #
+    #   * A training plan for SageMaker endpoints can be used exclusively to
+    #     provide compute resources to SageMaker endpoints for model
+    #     deployment.
     #   @return [Array<String>]
     #
     # @!attribute [rw] reserved_capacity_summaries
@@ -45661,7 +46045,7 @@ module Aws::SageMaker
     #
     # @!attribute [rw] target_resources
     #   The target resources (e.g., SageMaker Training Jobs, SageMaker
-    #   HyperPod) to search for in the offerings.
+    #   HyperPod, SageMaker Endpoints) to search for in the offerings.
     #
     #   Training plans are specific to their target resource.
     #
@@ -45670,6 +46054,10 @@ module Aws::SageMaker
     #
     #   * A training plan for HyperPod clusters can be used exclusively to
     #     provide compute resources to a cluster's instance group.
+    #
+    #   * A training plan for SageMaker endpoints can be used exclusively to
+    #     provide compute resources to SageMaker endpoints for model
+    #     deployment.
     #   @return [Array<String>]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/SearchTrainingPlanOfferingsRequest AWS API Documentation
@@ -48905,7 +49293,7 @@ module Aws::SageMaker
     #
     # @!attribute [rw] target_resources
     #   The target resources (e.g., SageMaker Training Jobs, SageMaker
-    #   HyperPod) for this training plan offering.
+    #   HyperPod, SageMaker Endpoints) for this training plan offering.
     #
     #   Training plans are specific to their target resource.
     #
@@ -48914,6 +49302,10 @@ module Aws::SageMaker
     #
     #   * A training plan for HyperPod clusters can be used exclusively to
     #     provide compute resources to a cluster's instance group.
+    #
+    #   * A training plan for SageMaker endpoints can be used exclusively to
+    #     provide compute resources to SageMaker endpoints for model
+    #     deployment.
     #   @return [Array<String>]
     #
     # @!attribute [rw] requested_start_time_after
@@ -49035,8 +49427,8 @@ module Aws::SageMaker
     #   @return [Integer]
     #
     # @!attribute [rw] target_resources
-    #   The target resources (e.g., training jobs, HyperPod clusters) that
-    #   can use this training plan.
+    #   The target resources (e.g., training jobs, HyperPod clusters,
+    #   Endpoints) that can use this training plan.
     #
     #   Training plans are specific to their target resource.
     #
@@ -49045,6 +49437,10 @@ module Aws::SageMaker
     #
     #   * A training plan for HyperPod clusters can be used exclusively to
     #     provide compute resources to a cluster's instance group.
+    #
+    #   * A training plan for SageMaker endpoints can be used exclusively to
+    #     provide compute resources to SageMaker endpoints for model
+    #     deployment.
     #   @return [Array<String>]
     #
     # @!attribute [rw] reserved_capacity_summaries

data/lib/aws-sdk-sagemaker.rb

@@ -55,7 +55,7 @@ module Aws::SageMaker
   autoload :EndpointProvider, 'aws-sdk-sagemaker/endpoint_provider'
   autoload :Endpoints, 'aws-sdk-sagemaker/endpoints'
 
-  GEM_VERSION = '1.339.0'
+  GEM_VERSION = '1.340.0'
 
 end
 

data/sig/client.rbs

@@ -181,6 +181,36 @@ module Aws
                                         ) -> _BatchDescribeModelPackageResponseSuccess
                                       | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _BatchDescribeModelPackageResponseSuccess
 
+      interface _BatchRebootClusterNodesResponseSuccess
+        include ::Seahorse::Client::_ResponseSuccess[Types::BatchRebootClusterNodesResponse]
+        def successful: () -> ::Array[::String]
+        def failed: () -> ::Array[Types::BatchRebootClusterNodesError]
+        def failed_node_logical_ids: () -> ::Array[Types::BatchRebootClusterNodeLogicalIdsError]
+        def successful_node_logical_ids: () -> ::Array[::String]
+      end
+      # https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMaker/Client.html#batch_reboot_cluster_nodes-instance_method
+      def batch_reboot_cluster_nodes: (
+                                        cluster_name: ::String,
+                                        ?node_ids: Array[::String],
+                                        ?node_logical_ids: Array[::String]
+                                      ) -> _BatchRebootClusterNodesResponseSuccess
+                                    | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _BatchRebootClusterNodesResponseSuccess
+
+      interface _BatchReplaceClusterNodesResponseSuccess
+        include ::Seahorse::Client::_ResponseSuccess[Types::BatchReplaceClusterNodesResponse]
+        def successful: () -> ::Array[::String]
+        def failed: () -> ::Array[Types::BatchReplaceClusterNodesError]
+        def failed_node_logical_ids: () -> ::Array[Types::BatchReplaceClusterNodeLogicalIdsError]
+        def successful_node_logical_ids: () -> ::Array[::String]
+      end
+      # https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMaker/Client.html#batch_replace_cluster_nodes-instance_method
+      def batch_replace_cluster_nodes: (
+                                         cluster_name: ::String,
+                                         ?node_ids: Array[::String],
+                                         ?node_logical_ids: Array[::String]
+                                       ) -> _BatchReplaceClusterNodesResponseSuccess
+                                     | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _BatchReplaceClusterNodesResponseSuccess
+
       interface _CreateActionResponseSuccess
         include ::Seahorse::Client::_ResponseSuccess[Types::CreateActionResponse]
         def action_arn: () -> ::String
@@ -1013,7 +1043,11 @@ module Aws
                                         count: ::Integer?,
                                         accelerators: ::Integer?,
                                         v_cpu: ::Float?,
-                                        memory_in_gi_b: ::Float?
+                                        memory_in_gi_b: ::Float?,
+                                        accelerator_partition: {
+                                          type: ("mig-1g.5gb" | "mig-1g.10gb" | "mig-1g.18gb" | "mig-1g.20gb" | "mig-1g.23gb" | "mig-1g.35gb" | "mig-1g.45gb" | "mig-1g.47gb" | "mig-2g.10gb" | "mig-2g.20gb" | "mig-2g.35gb" | "mig-2g.45gb" | "mig-2g.47gb" | "mig-3g.20gb" | "mig-3g.40gb" | "mig-3g.71gb" | "mig-3g.90gb" | "mig-3g.93gb" | "mig-4g.20gb" | "mig-4g.40gb" | "mig-4g.71gb" | "mig-4g.90gb" | "mig-4g.93gb" | "mig-7g.40gb" | "mig-7g.80gb" | "mig-7g.141gb" | "mig-7g.180gb" | "mig-7g.186gb"),
+                                          count: ::Integer
+                                        }?
                                       },
                                     ]?,
                                     resource_sharing_config: {
@@ -6680,7 +6714,7 @@ module Aws
         def unhealthy_instance_count: () -> ::Integer
         def available_spare_instance_count: () -> ::Integer
         def total_ultra_server_count: () -> ::Integer
-        def target_resources: () -> ::Array[("training-job" | "hyperpod-cluster")]
+        def target_resources: () -> ::Array[("training-job" | "hyperpod-cluster" | "endpoint")]
         def reserved_capacity_summaries: () -> ::Array[Types::ReservedCapacitySummary]
       end
       # https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMaker/Client.html#describe_training_plan-instance_method
@@ -8627,7 +8661,7 @@ module Aws
                                             ?start_time_after: ::Time,
                                             ?end_time_before: ::Time,
                                             duration_hours: ::Integer,
-                                            target_resources: Array[("training-job" | "hyperpod-cluster")]
+                                            target_resources: Array[("training-job" | "hyperpod-cluster" | "endpoint")]
                                           ) -> _SearchTrainingPlanOfferingsResponseSuccess
                                         | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _SearchTrainingPlanOfferingsResponseSuccess
 
@@ -9150,7 +9184,11 @@ module Aws
                                         count: ::Integer?,
                                         accelerators: ::Integer?,
                                         v_cpu: ::Float?,
-                                        memory_in_gi_b: ::Float?
+                                        memory_in_gi_b: ::Float?,
+                                        accelerator_partition: {
+                                          type: ("mig-1g.5gb" | "mig-1g.10gb" | "mig-1g.18gb" | "mig-1g.20gb" | "mig-1g.23gb" | "mig-1g.35gb" | "mig-1g.45gb" | "mig-1g.47gb" | "mig-2g.10gb" | "mig-2g.20gb" | "mig-2g.35gb" | "mig-2g.45gb" | "mig-2g.47gb" | "mig-3g.20gb" | "mig-3g.40gb" | "mig-3g.71gb" | "mig-3g.90gb" | "mig-3g.93gb" | "mig-4g.20gb" | "mig-4g.40gb" | "mig-4g.71gb" | "mig-4g.90gb" | "mig-4g.93gb" | "mig-7g.40gb" | "mig-7g.80gb" | "mig-7g.141gb" | "mig-7g.180gb" | "mig-7g.186gb"),
+                                          count: ::Integer
+                                        }?
                                       },
                                     ]?,
                                     resource_sharing_config: {

data/sig/types.rbs

@@ -8,6 +8,12 @@
 module Aws::SageMaker
   module Types
 
+    class AcceleratorPartitionConfig
+      attr_accessor type: ("mig-1g.5gb" | "mig-1g.10gb" | "mig-1g.18gb" | "mig-1g.20gb" | "mig-1g.23gb" | "mig-1g.35gb" | "mig-1g.45gb" | "mig-1g.47gb" | "mig-2g.10gb" | "mig-2g.20gb" | "mig-2g.35gb" | "mig-2g.45gb" | "mig-2g.47gb" | "mig-3g.20gb" | "mig-3g.40gb" | "mig-3g.71gb" | "mig-3g.90gb" | "mig-3g.93gb" | "mig-4g.20gb" | "mig-4g.40gb" | "mig-4g.71gb" | "mig-4g.90gb" | "mig-4g.93gb" | "mig-7g.40gb" | "mig-7g.80gb" | "mig-7g.141gb" | "mig-7g.180gb" | "mig-7g.186gb")
+      attr_accessor count: ::Integer
+      SENSITIVE: []
+    end
+
     class ActionSource
       attr_accessor source_uri: ::String
       attr_accessor source_type: ::String
@@ -598,6 +604,64 @@ module Aws::SageMaker
       SENSITIVE: []
     end
 
+    class BatchRebootClusterNodeLogicalIdsError
+      attr_accessor node_logical_id: ::String
+      attr_accessor error_code: ("InstanceIdNotFound" | "InvalidInstanceStatus" | "InstanceIdInUse" | "InternalServerError")
+      attr_accessor message: ::String
+      SENSITIVE: []
+    end
+
+    class BatchRebootClusterNodesError
+      attr_accessor node_id: ::String
+      attr_accessor error_code: ("InstanceIdNotFound" | "InvalidInstanceStatus" | "InstanceIdInUse" | "InternalServerError")
+      attr_accessor message: ::String
+      SENSITIVE: []
+    end
+
+    class BatchRebootClusterNodesRequest
+      attr_accessor cluster_name: ::String
+      attr_accessor node_ids: ::Array[::String]
+      attr_accessor node_logical_ids: ::Array[::String]
+      SENSITIVE: []
+    end
+
+    class BatchRebootClusterNodesResponse
+      attr_accessor successful: ::Array[::String]
+      attr_accessor failed: ::Array[Types::BatchRebootClusterNodesError]
+      attr_accessor failed_node_logical_ids: ::Array[Types::BatchRebootClusterNodeLogicalIdsError]
+      attr_accessor successful_node_logical_ids: ::Array[::String]
+      SENSITIVE: []
+    end
+
+    class BatchReplaceClusterNodeLogicalIdsError
+      attr_accessor node_logical_id: ::String
+      attr_accessor error_code: ("InstanceIdNotFound" | "InvalidInstanceStatus" | "InstanceIdInUse" | "InternalServerError")
+      attr_accessor message: ::String
+      SENSITIVE: []
+    end
+
+    class BatchReplaceClusterNodesError
+      attr_accessor node_id: ::String
+      attr_accessor error_code: ("InstanceIdNotFound" | "InvalidInstanceStatus" | "InstanceIdInUse" | "InternalServerError")
+      attr_accessor message: ::String
+      SENSITIVE: []
+    end
+
+    class BatchReplaceClusterNodesRequest
+      attr_accessor cluster_name: ::String
+      attr_accessor node_ids: ::Array[::String]
+      attr_accessor node_logical_ids: ::Array[::String]
+      SENSITIVE: []
+    end
+
+    class BatchReplaceClusterNodesResponse
+      attr_accessor successful: ::Array[::String]
+      attr_accessor failed: ::Array[Types::BatchReplaceClusterNodesError]
+      attr_accessor failed_node_logical_ids: ::Array[Types::BatchReplaceClusterNodeLogicalIdsError]
+      attr_accessor successful_node_logical_ids: ::Array[::String]
+      SENSITIVE: []
+    end
+
     class BatchTransformInput
       attr_accessor data_captured_destination_s3_uri: ::String
       attr_accessor dataset_format: Types::MonitoringDatasetFormat
@@ -1005,6 +1069,7 @@ module Aws::SageMaker
       attr_accessor last_software_update_time: ::Time
       attr_accessor instance_status: Types::ClusterInstanceStatusDetails
       attr_accessor ultra_server_info: Types::UltraServerInfo
+      attr_accessor private_dns_hostname: ::String
       SENSITIVE: []
     end
 
@@ -1165,6 +1230,7 @@ module Aws::SageMaker
       attr_accessor accelerators: ::Integer
       attr_accessor v_cpu: ::Float
       attr_accessor memory_in_gi_b: ::Float
+      attr_accessor accelerator_partition: Types::AcceleratorPartitionConfig
       SENSITIVE: []
     end
 
@@ -4388,7 +4454,7 @@ module Aws::SageMaker
       attr_accessor unhealthy_instance_count: ::Integer
       attr_accessor available_spare_instance_count: ::Integer
       attr_accessor total_ultra_server_count: ::Integer
-      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster")]
+      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster" | "endpoint")]
       attr_accessor reserved_capacity_summaries: ::Array[Types::ReservedCapacitySummary]
       SENSITIVE: []
     end
@@ -9567,7 +9633,7 @@ module Aws::SageMaker
       attr_accessor start_time_after: ::Time
       attr_accessor end_time_before: ::Time
       attr_accessor duration_hours: ::Integer
-      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster")]
+      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster" | "endpoint")]
       SENSITIVE: []
     end
 
@@ -10224,7 +10290,7 @@ module Aws::SageMaker
 
     class TrainingPlanOffering
       attr_accessor training_plan_offering_id: ::String
-      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster")]
+      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster" | "endpoint")]
       attr_accessor requested_start_time_after: ::Time
       attr_accessor requested_end_time_before: ::Time
       attr_accessor duration_hours: ::Integer
@@ -10250,7 +10316,7 @@ module Aws::SageMaker
       attr_accessor available_instance_count: ::Integer
       attr_accessor in_use_instance_count: ::Integer
       attr_accessor total_ultra_server_count: ::Integer
-      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster")]
+      attr_accessor target_resources: ::Array[("training-job" | "hyperpod-cluster" | "endpoint")]
       attr_accessor reserved_capacity_summaries: ::Array[Types::ReservedCapacitySummary]
       SENSITIVE: []
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.339.0
+  version: 1.340.0
 platform: ruby
 authors:
 - Amazon Web Services