aws-sdk-sagemaker 1.417.0 → 1.419.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -550,6 +550,73 @@ module Aws::SageMaker
550
550
  req.send_request(options)
551
551
  end
552
552
 
553
+ # Adds an in-cluster inference gateway to a global inference gateway.
554
+ # This operation is asynchronous: the in-cluster inference gateway
555
+ # starts in the `ADDING` status. To check its status, call
556
+ # `ListInferenceGateways`. If the in-cluster inference gateway is
557
+ # already in the global inference gateway, the operation succeeds and
558
+ # returns its current status.
559
+ #
560
+ # An in-cluster inference gateway can belong to only one global
561
+ # inference gateway. If it already belongs to another global inference
562
+ # gateway, the operation fails with `ResourceInUse`. The operation fails
563
+ # with `ConflictException` while another operation is in progress on the
564
+ # global inference gateway, or if the global inference gateway failed to
565
+ # create.
566
+ #
567
+ # @option params [required, String] :identifier
568
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
569
+ # gateway.
570
+ #
571
+ # @option params [required, String] :cluster_arn
572
+ # The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster that
573
+ # runs the in-cluster inference gateway. The cluster must be in the same
574
+ # account and partition as the global inference gateway. It can be in a
575
+ # different Region, but not in an opt-in Region.
576
+ #
577
+ # @option params [required, String] :namespace
578
+ # The Kubernetes namespace of the in-cluster inference gateway.
579
+ #
580
+ # @option params [required, String] :name
581
+ # The name of the `InferenceGatewayConfig` resource that defines the
582
+ # in-cluster inference gateway.
583
+ #
584
+ # @return [Types::AddInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
585
+ #
586
+ # * {Types::AddInferenceGatewayResponse#arn #arn} => String
587
+ # * {Types::AddInferenceGatewayResponse#id #id} => String
588
+ # * {Types::AddInferenceGatewayResponse#name #name} => String
589
+ # * {Types::AddInferenceGatewayResponse#gateway #gateway} => Types::GlobalInferenceGatewayMember
590
+ # * {Types::AddInferenceGatewayResponse#status #status} => String
591
+ #
592
+ # @example Request syntax with placeholder values
593
+ #
594
+ # resp = client.add_inference_gateway({
595
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
596
+ # cluster_arn: "GlobalInferenceGatewayClusterArn", # required
597
+ # namespace: "GlobalInferenceGatewayKubernetesNamespace", # required
598
+ # name: "GlobalInferenceGatewayKubernetesResourceName", # required
599
+ # })
600
+ #
601
+ # @example Response structure
602
+ #
603
+ # resp.arn #=> String
604
+ # resp.id #=> String
605
+ # resp.name #=> String
606
+ # resp.gateway.name #=> String
607
+ # resp.gateway.namespace #=> String
608
+ # resp.gateway.cluster_arn #=> String
609
+ # resp.status #=> String, one of "ADDING", "ACTIVE", "REMOVING", "FAILED"
610
+ #
611
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AddInferenceGateway AWS API Documentation
612
+ #
613
+ # @overload add_inference_gateway(params = {})
614
+ # @param [Hash] params ({})
615
+ def add_inference_gateway(params = {}, options = {})
616
+ req = build_request(:add_inference_gateway, params)
617
+ req.send_request(options)
618
+ end
619
+
553
620
  # Adds or overwrites one or more tags for the specified SageMaker
554
621
  # resource. You can add tags to notebook instances, training jobs,
555
622
  # hyperparameter tuning jobs, batch transform jobs, models, labeling
@@ -834,7 +901,7 @@ module Aws::SageMaker
834
901
  # resp.successful #=> Array
835
902
  # resp.successful[0].node_logical_id #=> String
836
903
  # resp.successful[0].instance_group_name #=> String
837
- # resp.successful[0].status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound"
904
+ # resp.successful[0].status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound", "DetachInProgress", "AttachInProgress"
838
905
  # resp.successful[0].availability_zones #=> Array
839
906
  # resp.successful[0].availability_zones[0] #=> String
840
907
  # resp.successful[0].instance_types #=> Array
@@ -5591,6 +5658,125 @@ module Aws::SageMaker
5591
5658
  req.send_request(options)
5592
5659
  end
5593
5660
 
5661
+ # Creates a global inference gateway. This operation is asynchronous:
5662
+ # the global inference gateway starts in the `CREATING` status. To check
5663
+ # its status, call `DescribeGlobalInferenceGateway` until the status is
5664
+ # `ACTIVE` or `FAILED`. The operation fails with `ResourceInUse` if the
5665
+ # name is already in use, or if one of the in-cluster inference gateways
5666
+ # in `Gateways` already belongs to another global inference gateway.
5667
+ #
5668
+ # @option params [required, String] :name
5669
+ # The name of the global inference gateway. The name must be unique in
5670
+ # your account in the current Region, and is case-sensitive. The name
5671
+ # can't be exactly 12 lowercase letters or digits, because the global
5672
+ # inference gateway ID uses that format.
5673
+ #
5674
+ # @option params [Types::GlobalInferenceGatewayRouting] :routing
5675
+ # The routing configuration of the global inference gateway. If you omit
5676
+ # it, the global inference gateway uses default routing weights.
5677
+ #
5678
+ # @option params [required, String] :execution_role_arn
5679
+ # The Amazon Resource Name (ARN) of the IAM role that the global
5680
+ # inference gateway assumes to access your SageMaker HyperPod clusters.
5681
+ # The role must be in your account and partition, and you must have
5682
+ # `iam:PassRole` permission for it. You can't change the role after you
5683
+ # create the global inference gateway.
5684
+ #
5685
+ # @option params [required, Array<Types::GlobalInferenceGatewayMember>] :gateways
5686
+ # The 1 to 10 in-cluster inference gateways to add to the global
5687
+ # inference gateway. A global inference gateway must always have at
5688
+ # least one in-cluster inference gateway, so `RemoveInferenceGateway`
5689
+ # can't remove the last one.
5690
+ #
5691
+ # @option params [String] :client_token
5692
+ # A unique, case-sensitive identifier that you provide to ensure the
5693
+ # idempotency of the request. An idempotent operation completes no more
5694
+ # than one time. If you don't specify a client token, the Amazon Web
5695
+ # Services SDKs and the Amazon Web Services CLI generate one for you.
5696
+ #
5697
+ # **A suitable default value is auto-generated.** You should normally
5698
+ # not need to pass this option.**
5699
+ #
5700
+ # @option params [Array<Types::Tag>] :tags
5701
+ # Custom tags for managing the global inference gateway as an Amazon Web
5702
+ # Services resource. You can add tags to your global inference gateway
5703
+ # in the same way you add them in other Amazon Web Services services
5704
+ # that support tagging. For more information about tagging Amazon Web
5705
+ # Services resources, see [Tagging your Amazon Web Services
5706
+ # resources][1] in the *Tagging Amazon Web Services Resources User
5707
+ # Guide*.
5708
+ #
5709
+ # The global inference gateway doesn't return tags in its responses. To
5710
+ # read the tags, use `ListTags`.
5711
+ #
5712
+ #
5713
+ #
5714
+ # [1]: https://docs.aws.amazon.com/tag-editor/latest/userguide/tagging.html
5715
+ #
5716
+ # @return [Types::CreateGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
5717
+ #
5718
+ # * {Types::CreateGlobalInferenceGatewayResponse#arn #arn} => String
5719
+ # * {Types::CreateGlobalInferenceGatewayResponse#id #id} => String
5720
+ # * {Types::CreateGlobalInferenceGatewayResponse#name #name} => String
5721
+ # * {Types::CreateGlobalInferenceGatewayResponse#status #status} => String
5722
+ # * {Types::CreateGlobalInferenceGatewayResponse#execution_role_arn #execution_role_arn} => String
5723
+ # * {Types::CreateGlobalInferenceGatewayResponse#routing #routing} => Types::GlobalInferenceGatewayRouting
5724
+ # * {Types::CreateGlobalInferenceGatewayResponse#gateways #gateways} => Array&lt;Types::GlobalInferenceGatewayMember&gt;
5725
+ #
5726
+ # @example Request syntax with placeholder values
5727
+ #
5728
+ # resp = client.create_global_inference_gateway({
5729
+ # name: "GlobalInferenceGatewayName", # required
5730
+ # routing: {
5731
+ # weights: { # required
5732
+ # kv_headroom: 1.0,
5733
+ # queue_depth: 1.0,
5734
+ # region_proximity: 1.0,
5735
+ # error_rate: 1.0,
5736
+ # },
5737
+ # },
5738
+ # execution_role_arn: "GlobalInferenceGatewayExecutionRoleArn", # required
5739
+ # gateways: [ # required
5740
+ # {
5741
+ # name: "GlobalInferenceGatewayKubernetesResourceName", # required
5742
+ # namespace: "GlobalInferenceGatewayKubernetesNamespace", # required
5743
+ # cluster_arn: "GlobalInferenceGatewayClusterArn", # required
5744
+ # },
5745
+ # ],
5746
+ # client_token: "GlobalInferenceGatewayClientToken",
5747
+ # tags: [
5748
+ # {
5749
+ # key: "TagKey", # required
5750
+ # value: "TagValue", # required
5751
+ # },
5752
+ # ],
5753
+ # })
5754
+ #
5755
+ # @example Response structure
5756
+ #
5757
+ # resp.arn #=> String
5758
+ # resp.id #=> String
5759
+ # resp.name #=> String
5760
+ # resp.status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
5761
+ # resp.execution_role_arn #=> String
5762
+ # resp.routing.weights.kv_headroom #=> Float
5763
+ # resp.routing.weights.queue_depth #=> Float
5764
+ # resp.routing.weights.region_proximity #=> Float
5765
+ # resp.routing.weights.error_rate #=> Float
5766
+ # resp.gateways #=> Array
5767
+ # resp.gateways[0].name #=> String
5768
+ # resp.gateways[0].namespace #=> String
5769
+ # resp.gateways[0].cluster_arn #=> String
5770
+ #
5771
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CreateGlobalInferenceGateway AWS API Documentation
5772
+ #
5773
+ # @overload create_global_inference_gateway(params = {})
5774
+ # @param [Hash] params ({})
5775
+ def create_global_inference_gateway(params = {}, options = {})
5776
+ req = build_request(:create_global_inference_gateway, params)
5777
+ req.send_request(options)
5778
+ end
5779
+
5594
5780
  # Create a hub.
5595
5781
  #
5596
5782
  # @option params [required, String] :hub_name
@@ -13457,6 +13643,47 @@ module Aws::SageMaker
13457
13643
  req.send_request(options)
13458
13644
  end
13459
13645
 
13646
+ # Delete a global inference gateway and its member inference gateways,
13647
+ # which are then free to join another global inference gateway.
13648
+ # Asynchronous: the global inference gateway is DELETING while its
13649
+ # managed endpoint resources are torn down; poll
13650
+ # DescribeGlobalInferenceGateway until it returns ResourceNotFound. Does
13651
+ # not touch the customer's clusters. Idempotent: a Delete whose
13652
+ # Identifier matches no global inference gateway succeeds and echoes
13653
+ # what the Identifier says (Arn and Id for an ARN or Id, Name for a
13654
+ # name).
13655
+ #
13656
+ # @option params [required, String] :identifier
13657
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
13658
+ # gateway to delete.
13659
+ #
13660
+ # @return [Types::DeleteGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
13661
+ #
13662
+ # * {Types::DeleteGlobalInferenceGatewayResponse#arn #arn} => String
13663
+ # * {Types::DeleteGlobalInferenceGatewayResponse#id #id} => String
13664
+ # * {Types::DeleteGlobalInferenceGatewayResponse#name #name} => String
13665
+ #
13666
+ # @example Request syntax with placeholder values
13667
+ #
13668
+ # resp = client.delete_global_inference_gateway({
13669
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
13670
+ # })
13671
+ #
13672
+ # @example Response structure
13673
+ #
13674
+ # resp.arn #=> String
13675
+ # resp.id #=> String
13676
+ # resp.name #=> String
13677
+ #
13678
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DeleteGlobalInferenceGateway AWS API Documentation
13679
+ #
13680
+ # @overload delete_global_inference_gateway(params = {})
13681
+ # @param [Hash] params ({})
13682
+ def delete_global_inference_gateway(params = {}, options = {})
13683
+ req = build_request(:delete_global_inference_gateway, params)
13684
+ req.send_request(options)
13685
+ end
13686
+
13460
13687
  # Delete a hub.
13461
13688
  #
13462
13689
  # @option params [required, String] :hub_name
@@ -15615,6 +15842,48 @@ module Aws::SageMaker
15615
15842
  req.send_request(options)
15616
15843
  end
15617
15844
 
15845
+ # Returns details about a SageMaker Capacity Reservation, such as its
15846
+ # instance type, instance count, Availability Zone, and start and end
15847
+ # times.
15848
+ #
15849
+ # @option params [required, String] :sm_capacity_reservation_arn
15850
+ # The Amazon Resource Name (ARN) of the SageMaker Capacity Reservation.
15851
+ # The ARN has the format
15852
+ # `arn:aws:sagemaker:region:account-id:sm-capacity-reservation/smcr-id`.
15853
+ #
15854
+ # @return [Types::DescribeCapacityReservationResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
15855
+ #
15856
+ # * {Types::DescribeCapacityReservationResponse#capacity_reservation #capacity_reservation} => Types::CapacityReservationDetail
15857
+ #
15858
+ # @example Request syntax with placeholder values
15859
+ #
15860
+ # resp = client.describe_capacity_reservation({
15861
+ # sm_capacity_reservation_arn: "CapacityReservationArn", # required
15862
+ # })
15863
+ #
15864
+ # @example Response structure
15865
+ #
15866
+ # resp.capacity_reservation.sm_capacity_reservation_arn #=> String
15867
+ # resp.capacity_reservation.sm_capacity_reservation_id #=> String
15868
+ # resp.capacity_reservation.owner #=> String
15869
+ # resp.capacity_reservation.status #=> String, one of "Scheduled", "Active", "Expired"
15870
+ # resp.capacity_reservation.instance_type #=> String
15871
+ # resp.capacity_reservation.availability_zone #=> String
15872
+ # resp.capacity_reservation.availability_zone_id #=> String
15873
+ # resp.capacity_reservation.total_instance_count #=> Integer
15874
+ # resp.capacity_reservation.start_time #=> Time
15875
+ # resp.capacity_reservation.end_time #=> Time
15876
+ # resp.capacity_reservation.creation_time #=> Time
15877
+ #
15878
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeCapacityReservation AWS API Documentation
15879
+ #
15880
+ # @overload describe_capacity_reservation(params = {})
15881
+ # @param [Hash] params ({})
15882
+ def describe_capacity_reservation(params = {}, options = {})
15883
+ req = build_request(:describe_capacity_reservation, params)
15884
+ req.send_request(options)
15885
+ end
15886
+
15618
15887
  # Retrieves information of a SageMaker HyperPod cluster.
15619
15888
  #
15620
15889
  # @option params [required, String] :cluster_name
@@ -15730,7 +15999,7 @@ module Aws::SageMaker
15730
15999
  # resp.instance_groups[0].kubernetes_config.desired_taints[0].value #=> String
15731
16000
  # resp.instance_groups[0].kubernetes_config.desired_taints[0].effect #=> String, one of "NoSchedule", "PreferNoSchedule", "NoExecute"
15732
16001
  # resp.instance_groups[0].target_state_count #=> Integer
15733
- # resp.instance_groups[0].software_update_status #=> String, one of "Pending", "InProgress", "Succeeded", "Failed", "RollbackInProgress", "RollbackComplete"
16002
+ # resp.instance_groups[0].software_update_status #=> String, one of "Pending", "InProgress", "Succeeded", "Failed", "RollbackInProgress", "RollbackComplete", "PartiallySucceeded"
15734
16003
  # resp.instance_groups[0].active_software_update_config.rolling_update_policy.maximum_batch_size.type #=> String, one of "INSTANCE_COUNT", "CAPACITY_PERCENTAGE"
15735
16004
  # resp.instance_groups[0].active_software_update_config.rolling_update_policy.maximum_batch_size.value #=> Integer
15736
16005
  # resp.instance_groups[0].active_software_update_config.rolling_update_policy.rollback_maximum_batch_size.type #=> String, one of "INSTANCE_COUNT", "CAPACITY_PERCENTAGE"
@@ -15981,7 +16250,7 @@ module Aws::SageMaker
15981
16250
  # resp.node_details.instance_group_name #=> String
15982
16251
  # resp.node_details.instance_id #=> String
15983
16252
  # resp.node_details.node_logical_id #=> String
15984
- # resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound"
16253
+ # resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound", "DetachInProgress", "AttachInProgress"
15985
16254
  # resp.node_details.instance_status.message #=> String
15986
16255
  # resp.node_details.instance_type #=> String, one of "ml.p4d.24xlarge", "ml.p4de.24xlarge", "ml.p5.48xlarge", "ml.p5.4xlarge", "ml.p6e-gb200.36xlarge", "ml.trn1.32xlarge", "ml.trn1n.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.12xlarge", "ml.c5.18xlarge", "ml.c5.24xlarge", "ml.c5n.large", "ml.c5n.2xlarge", "ml.c5n.4xlarge", "ml.c5n.9xlarge", "ml.c5n.18xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.8xlarge", "ml.m5.12xlarge", "ml.m5.16xlarge", "ml.m5.24xlarge", "ml.t3.medium", "ml.t3.large", "ml.t3.xlarge", "ml.t3.2xlarge", "ml.g6.xlarge", "ml.g6.2xlarge", "ml.g6.4xlarge", "ml.g6.8xlarge", "ml.g6.16xlarge", "ml.g6.12xlarge", "ml.g6.24xlarge", "ml.g6.48xlarge", "ml.gr6.4xlarge", "ml.gr6.8xlarge", "ml.g6e.xlarge", "ml.g6e.2xlarge", "ml.g6e.4xlarge", "ml.g6e.8xlarge", "ml.g6e.16xlarge", "ml.g6e.12xlarge", "ml.g6e.24xlarge", "ml.g6e.48xlarge", "ml.p5e.48xlarge", "ml.p5en.48xlarge", "ml.p6-b200.48xlarge", "ml.trn2.3xlarge", "ml.trn2.48xlarge", "ml.c6i.large", "ml.c6i.xlarge", "ml.c6i.2xlarge", "ml.c6i.4xlarge", "ml.c6i.8xlarge", "ml.c6i.12xlarge", "ml.c6i.16xlarge", "ml.c6i.24xlarge", "ml.c6i.32xlarge", "ml.m6i.large", "ml.m6i.xlarge", "ml.m6i.2xlarge", "ml.m6i.4xlarge", "ml.m6i.8xlarge", "ml.m6i.12xlarge", "ml.m6i.16xlarge", "ml.m6i.24xlarge", "ml.m6i.32xlarge", "ml.r6i.large", "ml.r6i.xlarge", "ml.r6i.2xlarge", "ml.r6i.4xlarge", "ml.r6i.8xlarge", "ml.r6i.12xlarge", "ml.r6i.16xlarge", "ml.r6i.24xlarge", "ml.r6i.32xlarge", "ml.i3en.large", "ml.i3en.xlarge", "ml.i3en.2xlarge", "ml.i3en.3xlarge", "ml.i3en.6xlarge", "ml.i3en.12xlarge", "ml.i3en.24xlarge", "ml.m7i.large", "ml.m7i.xlarge", "ml.m7i.2xlarge", "ml.m7i.4xlarge", "ml.m7i.8xlarge", "ml.m7i.12xlarge", "ml.m7i.16xlarge", "ml.m7i.24xlarge", "ml.m7i.48xlarge", "ml.r7i.large", "ml.r7i.xlarge", "ml.r7i.2xlarge", "ml.r7i.4xlarge", "ml.r7i.8xlarge", "ml.r7i.12xlarge", "ml.r7i.16xlarge", "ml.r7i.24xlarge", "ml.r7i.48xlarge", "ml.r5d.16xlarge", "ml.g7e.2xlarge", "ml.g7e.4xlarge", "ml.g7e.8xlarge", "ml.g7e.12xlarge", "ml.g7e.24xlarge", "ml.g7e.48xlarge", "ml.p6-b300.48xlarge", "ml.g4dn.xlarge", "ml.g4dn.2xlarge", "ml.g4dn.4xlarge", "ml.g4dn.8xlarge", "ml.g4dn.12xlarge", "ml.g4dn.16xlarge", "ml.c6g.medium", "ml.c6g.large", "ml.c6g.xlarge", "ml.c6g.2xlarge", "ml.c6g.4xlarge", "ml.c6g.8xlarge", "ml.c6g.12xlarge", "ml.c6g.16xlarge", "ml.c7g.medium", "ml.c7g.large", "ml.c7g.xlarge", "ml.c7g.2xlarge", "ml.c7g.4xlarge", "ml.c7g.8xlarge", "ml.c7g.12xlarge", "ml.c7g.16xlarge", "ml.c8g.medium", "ml.c8g.large", "ml.c8g.xlarge", "ml.c8g.2xlarge", "ml.c8g.4xlarge", "ml.c8g.8xlarge", "ml.c8g.12xlarge", "ml.c8g.16xlarge", "ml.c8g.24xlarge", "ml.c8g.48xlarge", "ml.c6a.large", "ml.c6a.xlarge", "ml.c6a.2xlarge", "ml.c6a.4xlarge", "ml.c6a.8xlarge", "ml.c6a.12xlarge", "ml.c6a.16xlarge", "ml.c6a.24xlarge", "ml.c6a.32xlarge", "ml.c6a.48xlarge", "ml.m6a.large", "ml.m6a.xlarge", "ml.m6a.2xlarge", "ml.m6a.4xlarge", "ml.m6a.8xlarge", "ml.m6a.12xlarge", "ml.m6a.16xlarge", "ml.m6a.24xlarge", "ml.m6a.32xlarge", "ml.m6a.48xlarge", "ml.m6g.medium", "ml.m6g.large", "ml.m6g.xlarge", "ml.m6g.2xlarge", "ml.m6g.4xlarge", "ml.m6g.8xlarge", "ml.m6g.12xlarge", "ml.m6g.16xlarge", "ml.m7g.medium", "ml.m7g.large", "ml.m7g.xlarge", "ml.m7g.2xlarge", "ml.m7g.4xlarge", "ml.m7g.8xlarge", "ml.m7g.12xlarge", "ml.m7g.16xlarge", "ml.m8g.medium", "ml.m8g.large", "ml.m8g.xlarge", "ml.m8g.2xlarge", "ml.m8g.4xlarge", "ml.m8g.8xlarge", "ml.m8g.12xlarge", "ml.m8g.16xlarge", "ml.m8g.24xlarge", "ml.m8g.48xlarge", "ml.g7.2xlarge", "ml.g7.4xlarge", "ml.g7.8xlarge", "ml.g7.12xlarge", "ml.g7.24xlarge", "ml.g7.48xlarge", "ml.c8a.16xlarge", "ml.m8a.16xlarge"
15987
16256
  # resp.node_details.launch_time #=> Time
@@ -17764,6 +18033,60 @@ module Aws::SageMaker
17764
18033
  req.send_request(options)
17765
18034
  end
17766
18035
 
18036
+ # Retrieves information about a global inference gateway, including its
18037
+ # status, endpoints, and routing configuration. To list the in-cluster
18038
+ # inference gateways of the global inference gateway, use
18039
+ # `ListInferenceGateways`. To read the tags of the global inference
18040
+ # gateway, use `ListTags`.
18041
+ #
18042
+ # @option params [required, String] :identifier
18043
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
18044
+ # gateway.
18045
+ #
18046
+ # @return [Types::DescribeGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
18047
+ #
18048
+ # * {Types::DescribeGlobalInferenceGatewayResponse#arn #arn} => String
18049
+ # * {Types::DescribeGlobalInferenceGatewayResponse#id #id} => String
18050
+ # * {Types::DescribeGlobalInferenceGatewayResponse#name #name} => String
18051
+ # * {Types::DescribeGlobalInferenceGatewayResponse#execution_role_arn #execution_role_arn} => String
18052
+ # * {Types::DescribeGlobalInferenceGatewayResponse#status #status} => String
18053
+ # * {Types::DescribeGlobalInferenceGatewayResponse#endpoint_url #endpoint_url} => String
18054
+ # * {Types::DescribeGlobalInferenceGatewayResponse#vpc_endpoint_service_name #vpc_endpoint_service_name} => String
18055
+ # * {Types::DescribeGlobalInferenceGatewayResponse#routing #routing} => Types::GlobalInferenceGatewayRouting
18056
+ # * {Types::DescribeGlobalInferenceGatewayResponse#creation_time #creation_time} => Time
18057
+ # * {Types::DescribeGlobalInferenceGatewayResponse#failure_reason #failure_reason} => String
18058
+ #
18059
+ # @example Request syntax with placeholder values
18060
+ #
18061
+ # resp = client.describe_global_inference_gateway({
18062
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
18063
+ # })
18064
+ #
18065
+ # @example Response structure
18066
+ #
18067
+ # resp.arn #=> String
18068
+ # resp.id #=> String
18069
+ # resp.name #=> String
18070
+ # resp.execution_role_arn #=> String
18071
+ # resp.status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
18072
+ # resp.endpoint_url #=> String
18073
+ # resp.vpc_endpoint_service_name #=> String
18074
+ # resp.routing.weights.kv_headroom #=> Float
18075
+ # resp.routing.weights.queue_depth #=> Float
18076
+ # resp.routing.weights.region_proximity #=> Float
18077
+ # resp.routing.weights.error_rate #=> Float
18078
+ # resp.creation_time #=> Time
18079
+ # resp.failure_reason #=> String
18080
+ #
18081
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeGlobalInferenceGateway AWS API Documentation
18082
+ #
18083
+ # @overload describe_global_inference_gateway(params = {})
18084
+ # @param [Hash] params ({})
18085
+ def describe_global_inference_gateway(params = {}, options = {})
18086
+ req = build_request(:describe_global_inference_gateway, params)
18087
+ req.send_request(options)
18088
+ end
18089
+
17767
18090
  # Describes a hub.
17768
18091
  #
17769
18092
  # @option params [required, String] :hub_name
@@ -20971,6 +21294,68 @@ module Aws::SageMaker
20971
21294
  req.send_request(options)
20972
21295
  end
20973
21296
 
21297
+ # Returns the resources in your account that are associated with a
21298
+ # SageMaker Capacity Reservation and the status of each association.
21299
+ # Resources include SageMaker AI HyperPod clusters and SageMaker AI
21300
+ # endpoints.
21301
+ #
21302
+ # @option params [required, String] :sm_capacity_reservation_arn
21303
+ # The Amazon Resource Name (ARN) of the SageMaker Capacity Reservation.
21304
+ # The ARN has the format
21305
+ # `arn:aws:sagemaker:region:account-id:sm-capacity-reservation/smcr-id`.
21306
+ #
21307
+ # @option params [Integer] :max_results
21308
+ # The maximum number of results to return in the response. If more
21309
+ # results are available, the response includes a `NextToken` value.
21310
+ #
21311
+ # @option params [String] :next_token
21312
+ # If the previous response was truncated, the response includes a
21313
+ # `NextToken` value. To retrieve the next set of results, use that token
21314
+ # in your next request.
21315
+ #
21316
+ # @return [Types::DescribeResourceAssociationsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
21317
+ #
21318
+ # * {Types::DescribeResourceAssociationsResponse#sm_capacity_reservation_arn #sm_capacity_reservation_arn} => String
21319
+ # * {Types::DescribeResourceAssociationsResponse#sm_capacity_reservation_id #sm_capacity_reservation_id} => String
21320
+ # * {Types::DescribeResourceAssociationsResponse#resource_associations #resource_associations} => Array&lt;Types::CapacityReservationResourceAssociation&gt;
21321
+ # * {Types::DescribeResourceAssociationsResponse#next_token #next_token} => String
21322
+ #
21323
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
21324
+ #
21325
+ # @example Request syntax with placeholder values
21326
+ #
21327
+ # resp = client.describe_resource_associations({
21328
+ # sm_capacity_reservation_arn: "CapacityReservationArn", # required
21329
+ # max_results: 1,
21330
+ # next_token: "NextToken",
21331
+ # })
21332
+ #
21333
+ # @example Response structure
21334
+ #
21335
+ # resp.sm_capacity_reservation_arn #=> String
21336
+ # resp.sm_capacity_reservation_id #=> String
21337
+ # resp.resource_associations #=> Array
21338
+ # resp.resource_associations[0].hyper_pod_clusters.status #=> String, one of "Pending", "Active", "Inactive"
21339
+ # resp.resource_associations[0].hyper_pod_clusters.failure_reason #=> String
21340
+ # resp.resource_associations[0].hyper_pod_clusters.associated_time #=> Time
21341
+ # resp.resource_associations[0].endpoints.ml_reservation_id #=> String
21342
+ # resp.resource_associations[0].endpoints.status #=> String, one of "Pending", "Active", "Inactive"
21343
+ # resp.resource_associations[0].endpoints.match_criteria #=> String, one of "Open", "Targeted"
21344
+ # resp.resource_associations[0].endpoints.endpoint_sharing #=> String, one of "SingleEndpoint", "MultipleEndpoints"
21345
+ # resp.resource_associations[0].endpoints.ml_reservation_arn #=> String
21346
+ # resp.resource_associations[0].endpoints.failure_reason #=> String
21347
+ # resp.resource_associations[0].endpoints.associated_time #=> Time
21348
+ # resp.next_token #=> String
21349
+ #
21350
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeResourceAssociations AWS API Documentation
21351
+ #
21352
+ # @overload describe_resource_associations(params = {})
21353
+ # @param [Hash] params ({})
21354
+ def describe_resource_associations(params = {}, options = {})
21355
+ req = build_request(:describe_resource_associations, params)
21356
+ req.send_request(options)
21357
+ end
21358
+
20974
21359
  # Describes the space.
20975
21360
  #
20976
21361
  # @option params [required, String] :domain_id
@@ -22323,6 +22708,68 @@ module Aws::SageMaker
22323
22708
  req.send_request(options)
22324
22709
  end
22325
22710
 
22711
+ # Returns the number of instances in use from a SageMaker Capacity
22712
+ # Reservation, for each account that uses them.
22713
+ #
22714
+ # SageMaker AI refreshes the usage counts periodically. The
22715
+ # `LastRefreshTime` value shows when the counts were last refreshed.
22716
+ #
22717
+ # @option params [required, String] :sm_capacity_reservation_arn
22718
+ # The Amazon Resource Name (ARN) of the SageMaker Capacity Reservation.
22719
+ # The ARN has the format
22720
+ # `arn:aws:sagemaker:region:account-id:sm-capacity-reservation/smcr-id`.
22721
+ #
22722
+ # @option params [Integer] :max_results
22723
+ # The maximum number of results to return in the response. If more
22724
+ # results are available, the response includes a `NextToken` value.
22725
+ #
22726
+ # @option params [String] :next_token
22727
+ # If the previous response was truncated, the response includes a
22728
+ # `NextToken` value. To retrieve the next set of results, use that token
22729
+ # in your next request.
22730
+ #
22731
+ # @return [Types::GetCapacityReservationUsageResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
22732
+ #
22733
+ # * {Types::GetCapacityReservationUsageResponse#sm_capacity_reservation_id #sm_capacity_reservation_id} => String
22734
+ # * {Types::GetCapacityReservationUsageResponse#total_instance_count #total_instance_count} => Integer
22735
+ # * {Types::GetCapacityReservationUsageResponse#available_instance_count #available_instance_count} => Integer
22736
+ # * {Types::GetCapacityReservationUsageResponse#last_refresh_time #last_refresh_time} => Time
22737
+ # * {Types::GetCapacityReservationUsageResponse#instance_usage_set #instance_usage_set} => Array&lt;Types::CapacityReservationInstanceUsage&gt;
22738
+ # * {Types::GetCapacityReservationUsageResponse#next_token #next_token} => String
22739
+ #
22740
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
22741
+ #
22742
+ # @example Request syntax with placeholder values
22743
+ #
22744
+ # resp = client.get_capacity_reservation_usage({
22745
+ # sm_capacity_reservation_arn: "CapacityReservationArn", # required
22746
+ # max_results: 1,
22747
+ # next_token: "NextToken",
22748
+ # })
22749
+ #
22750
+ # @example Response structure
22751
+ #
22752
+ # resp.sm_capacity_reservation_id #=> String
22753
+ # resp.total_instance_count #=> Integer
22754
+ # resp.available_instance_count #=> Integer
22755
+ # resp.last_refresh_time #=> Time
22756
+ # resp.instance_usage_set #=> Array
22757
+ # resp.instance_usage_set[0].account_id #=> String
22758
+ # resp.instance_usage_set[0].in_use_instance_count #=> Integer
22759
+ # resp.instance_usage_set[0].resources_usage #=> Array
22760
+ # resp.instance_usage_set[0].resources_usage[0].resource_type #=> String, one of "HyperPodClusters", "Endpoints"
22761
+ # resp.instance_usage_set[0].resources_usage[0].in_use_instance_count #=> Integer
22762
+ # resp.next_token #=> String
22763
+ #
22764
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/GetCapacityReservationUsage AWS API Documentation
22765
+ #
22766
+ # @overload get_capacity_reservation_usage(params = {})
22767
+ # @param [Hash] params ({})
22768
+ def get_capacity_reservation_usage(params = {}, options = {})
22769
+ req = build_request(:get_capacity_reservation_usage, params)
22770
+ req.send_request(options)
22771
+ end
22772
+
22326
22773
  # Describes a fleet.
22327
22774
  #
22328
22775
  # @option params [required, String] :device_fleet_name
@@ -23627,6 +24074,69 @@ module Aws::SageMaker
23627
24074
  req.send_request(options)
23628
24075
  end
23629
24076
 
24077
+ # Lists the SageMaker Capacity Reservations in your account.
24078
+ #
24079
+ # An empty list is a valid response.
24080
+ #
24081
+ # @option params [Integer] :max_results
24082
+ # The maximum number of results to return in the response. If more
24083
+ # results are available, the response includes a `NextToken` value.
24084
+ #
24085
+ # @option params [String] :next_token
24086
+ # If the previous response was truncated, the response includes a
24087
+ # `NextToken` value. To retrieve the next set of results, use that token
24088
+ # in your next request.
24089
+ #
24090
+ # @option params [Array<Types::CapacityReservationFilter>] :filters
24091
+ # A filter that returns only the reservations that match it. You can
24092
+ # specify one filter. If you don't specify a filter, the response
24093
+ # includes all reservations in your account.
24094
+ #
24095
+ # @return [Types::ListCapacityReservationsResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
24096
+ #
24097
+ # * {Types::ListCapacityReservationsResponse#capacity_reservation_summaries #capacity_reservation_summaries} => Array&lt;Types::CapacityReservationSummary&gt;
24098
+ # * {Types::ListCapacityReservationsResponse#next_token #next_token} => String
24099
+ #
24100
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
24101
+ #
24102
+ # @example Request syntax with placeholder values
24103
+ #
24104
+ # resp = client.list_capacity_reservations({
24105
+ # max_results: 1,
24106
+ # next_token: "NextToken",
24107
+ # filters: [
24108
+ # {
24109
+ # name: "Status", # required, accepts Status
24110
+ # values: ["CapacityReservationFilterValue"], # required
24111
+ # },
24112
+ # ],
24113
+ # })
24114
+ #
24115
+ # @example Response structure
24116
+ #
24117
+ # resp.capacity_reservation_summaries #=> Array
24118
+ # resp.capacity_reservation_summaries[0].sm_capacity_reservation_arn #=> String
24119
+ # resp.capacity_reservation_summaries[0].sm_capacity_reservation_id #=> String
24120
+ # resp.capacity_reservation_summaries[0].owner #=> String
24121
+ # resp.capacity_reservation_summaries[0].status #=> String, one of "Scheduled", "Active", "Expired"
24122
+ # resp.capacity_reservation_summaries[0].instance_type #=> String
24123
+ # resp.capacity_reservation_summaries[0].availability_zone #=> String
24124
+ # resp.capacity_reservation_summaries[0].availability_zone_id #=> String
24125
+ # resp.capacity_reservation_summaries[0].total_instance_count #=> Integer
24126
+ # resp.capacity_reservation_summaries[0].start_time #=> Time
24127
+ # resp.capacity_reservation_summaries[0].end_time #=> Time
24128
+ # resp.capacity_reservation_summaries[0].creation_time #=> Time
24129
+ # resp.next_token #=> String
24130
+ #
24131
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListCapacityReservations AWS API Documentation
24132
+ #
24133
+ # @overload list_capacity_reservations(params = {})
24134
+ # @param [Hash] params ({})
24135
+ def list_capacity_reservations(params = {}, options = {})
24136
+ req = build_request(:list_capacity_reservations, params)
24137
+ req.send_request(options)
24138
+ end
24139
+
23630
24140
  # Retrieves a list of event summaries for a specified HyperPod cluster.
23631
24141
  # The operation supports filtering, sorting, and pagination of results.
23632
24142
  # This functionality is only supported when the `NodeProvisioningMode`
@@ -23943,7 +24453,7 @@ module Aws::SageMaker
23943
24453
  # resp.cluster_node_summaries[0].instance_type #=> String, one of "ml.p4d.24xlarge", "ml.p4de.24xlarge", "ml.p5.48xlarge", "ml.p5.4xlarge", "ml.p6e-gb200.36xlarge", "ml.trn1.32xlarge", "ml.trn1n.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.12xlarge", "ml.c5.18xlarge", "ml.c5.24xlarge", "ml.c5n.large", "ml.c5n.2xlarge", "ml.c5n.4xlarge", "ml.c5n.9xlarge", "ml.c5n.18xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.8xlarge", "ml.m5.12xlarge", "ml.m5.16xlarge", "ml.m5.24xlarge", "ml.t3.medium", "ml.t3.large", "ml.t3.xlarge", "ml.t3.2xlarge", "ml.g6.xlarge", "ml.g6.2xlarge", "ml.g6.4xlarge", "ml.g6.8xlarge", "ml.g6.16xlarge", "ml.g6.12xlarge", "ml.g6.24xlarge", "ml.g6.48xlarge", "ml.gr6.4xlarge", "ml.gr6.8xlarge", "ml.g6e.xlarge", "ml.g6e.2xlarge", "ml.g6e.4xlarge", "ml.g6e.8xlarge", "ml.g6e.16xlarge", "ml.g6e.12xlarge", "ml.g6e.24xlarge", "ml.g6e.48xlarge", "ml.p5e.48xlarge", "ml.p5en.48xlarge", "ml.p6-b200.48xlarge", "ml.trn2.3xlarge", "ml.trn2.48xlarge", "ml.c6i.large", "ml.c6i.xlarge", "ml.c6i.2xlarge", "ml.c6i.4xlarge", "ml.c6i.8xlarge", "ml.c6i.12xlarge", "ml.c6i.16xlarge", "ml.c6i.24xlarge", "ml.c6i.32xlarge", "ml.m6i.large", "ml.m6i.xlarge", "ml.m6i.2xlarge", "ml.m6i.4xlarge", "ml.m6i.8xlarge", "ml.m6i.12xlarge", "ml.m6i.16xlarge", "ml.m6i.24xlarge", "ml.m6i.32xlarge", "ml.r6i.large", "ml.r6i.xlarge", "ml.r6i.2xlarge", "ml.r6i.4xlarge", "ml.r6i.8xlarge", "ml.r6i.12xlarge", "ml.r6i.16xlarge", "ml.r6i.24xlarge", "ml.r6i.32xlarge", "ml.i3en.large", "ml.i3en.xlarge", "ml.i3en.2xlarge", "ml.i3en.3xlarge", "ml.i3en.6xlarge", "ml.i3en.12xlarge", "ml.i3en.24xlarge", "ml.m7i.large", "ml.m7i.xlarge", "ml.m7i.2xlarge", "ml.m7i.4xlarge", "ml.m7i.8xlarge", "ml.m7i.12xlarge", "ml.m7i.16xlarge", "ml.m7i.24xlarge", "ml.m7i.48xlarge", "ml.r7i.large", "ml.r7i.xlarge", "ml.r7i.2xlarge", "ml.r7i.4xlarge", "ml.r7i.8xlarge", "ml.r7i.12xlarge", "ml.r7i.16xlarge", "ml.r7i.24xlarge", "ml.r7i.48xlarge", "ml.r5d.16xlarge", "ml.g7e.2xlarge", "ml.g7e.4xlarge", "ml.g7e.8xlarge", "ml.g7e.12xlarge", "ml.g7e.24xlarge", "ml.g7e.48xlarge", "ml.p6-b300.48xlarge", "ml.g4dn.xlarge", "ml.g4dn.2xlarge", "ml.g4dn.4xlarge", "ml.g4dn.8xlarge", "ml.g4dn.12xlarge", "ml.g4dn.16xlarge", "ml.c6g.medium", "ml.c6g.large", "ml.c6g.xlarge", "ml.c6g.2xlarge", "ml.c6g.4xlarge", "ml.c6g.8xlarge", "ml.c6g.12xlarge", "ml.c6g.16xlarge", "ml.c7g.medium", "ml.c7g.large", "ml.c7g.xlarge", "ml.c7g.2xlarge", "ml.c7g.4xlarge", "ml.c7g.8xlarge", "ml.c7g.12xlarge", "ml.c7g.16xlarge", "ml.c8g.medium", "ml.c8g.large", "ml.c8g.xlarge", "ml.c8g.2xlarge", "ml.c8g.4xlarge", "ml.c8g.8xlarge", "ml.c8g.12xlarge", "ml.c8g.16xlarge", "ml.c8g.24xlarge", "ml.c8g.48xlarge", "ml.c6a.large", "ml.c6a.xlarge", "ml.c6a.2xlarge", "ml.c6a.4xlarge", "ml.c6a.8xlarge", "ml.c6a.12xlarge", "ml.c6a.16xlarge", "ml.c6a.24xlarge", "ml.c6a.32xlarge", "ml.c6a.48xlarge", "ml.m6a.large", "ml.m6a.xlarge", "ml.m6a.2xlarge", "ml.m6a.4xlarge", "ml.m6a.8xlarge", "ml.m6a.12xlarge", "ml.m6a.16xlarge", "ml.m6a.24xlarge", "ml.m6a.32xlarge", "ml.m6a.48xlarge", "ml.m6g.medium", "ml.m6g.large", "ml.m6g.xlarge", "ml.m6g.2xlarge", "ml.m6g.4xlarge", "ml.m6g.8xlarge", "ml.m6g.12xlarge", "ml.m6g.16xlarge", "ml.m7g.medium", "ml.m7g.large", "ml.m7g.xlarge", "ml.m7g.2xlarge", "ml.m7g.4xlarge", "ml.m7g.8xlarge", "ml.m7g.12xlarge", "ml.m7g.16xlarge", "ml.m8g.medium", "ml.m8g.large", "ml.m8g.xlarge", "ml.m8g.2xlarge", "ml.m8g.4xlarge", "ml.m8g.8xlarge", "ml.m8g.12xlarge", "ml.m8g.16xlarge", "ml.m8g.24xlarge", "ml.m8g.48xlarge", "ml.g7.2xlarge", "ml.g7.4xlarge", "ml.g7.8xlarge", "ml.g7.12xlarge", "ml.g7.24xlarge", "ml.g7.48xlarge", "ml.c8a.16xlarge", "ml.m8a.16xlarge"
23944
24454
  # resp.cluster_node_summaries[0].launch_time #=> Time
23945
24455
  # resp.cluster_node_summaries[0].last_software_update_time #=> Time
23946
- # resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound"
24456
+ # resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound", "DetachInProgress", "AttachInProgress"
23947
24457
  # resp.cluster_node_summaries[0].instance_status.message #=> String
23948
24458
  # resp.cluster_node_summaries[0].ultra_server_info.id #=> String
23949
24459
  # resp.cluster_node_summaries[0].ultra_server_info.type #=> String
@@ -25356,6 +25866,62 @@ module Aws::SageMaker
25356
25866
  req.send_request(options)
25357
25867
  end
25358
25868
 
25869
+ # Lists summaries of the global inference gateways in your account. You
25870
+ # can filter the results by status.
25871
+ #
25872
+ # @option params [Array<Types::GlobalInferenceGatewayFilter>] :filters
25873
+ # The filters to apply to the results. You can filter by `Status`.
25874
+ # Multiple filters are combined with a logical AND.
25875
+ #
25876
+ # @option params [String] :next_token
25877
+ # If the result of the previous `ListGlobalInferenceGateways` request
25878
+ # was truncated, the response includes a `NextToken`. To retrieve the
25879
+ # next set of global inference gateways, use the token in the next
25880
+ # request.
25881
+ #
25882
+ # @option params [Integer] :max_results
25883
+ # The maximum number of global inference gateways to return in the
25884
+ # response.
25885
+ #
25886
+ # @return [Types::ListGlobalInferenceGatewaysResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
25887
+ #
25888
+ # * {Types::ListGlobalInferenceGatewaysResponse#global_inference_gateway_summaries #global_inference_gateway_summaries} => Array&lt;Types::GlobalInferenceGatewaySummary&gt;
25889
+ # * {Types::ListGlobalInferenceGatewaysResponse#next_token #next_token} => String
25890
+ #
25891
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
25892
+ #
25893
+ # @example Request syntax with placeholder values
25894
+ #
25895
+ # resp = client.list_global_inference_gateways({
25896
+ # filters: [
25897
+ # {
25898
+ # name: "Status", # required, accepts Status
25899
+ # value: "GlobalInferenceGatewayFilterValue", # required
25900
+ # },
25901
+ # ],
25902
+ # next_token: "GlobalInferenceGatewayNextToken",
25903
+ # max_results: 1,
25904
+ # })
25905
+ #
25906
+ # @example Response structure
25907
+ #
25908
+ # resp.global_inference_gateway_summaries #=> Array
25909
+ # resp.global_inference_gateway_summaries[0].arn #=> String
25910
+ # resp.global_inference_gateway_summaries[0].id #=> String
25911
+ # resp.global_inference_gateway_summaries[0].name #=> String
25912
+ # resp.global_inference_gateway_summaries[0].status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
25913
+ # resp.global_inference_gateway_summaries[0].creation_time #=> Time
25914
+ # resp.next_token #=> String
25915
+ #
25916
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListGlobalInferenceGateways AWS API Documentation
25917
+ #
25918
+ # @overload list_global_inference_gateways(params = {})
25919
+ # @param [Hash] params ({})
25920
+ def list_global_inference_gateways(params = {}, options = {})
25921
+ req = build_request(:list_global_inference_gateways, params)
25922
+ req.send_request(options)
25923
+ end
25924
+
25359
25925
  # List hub content versions.
25360
25926
  #
25361
25927
  # @option params [required, String] :hub_name
@@ -26112,6 +26678,71 @@ module Aws::SageMaker
26112
26678
  req.send_request(options)
26113
26679
  end
26114
26680
 
26681
+ # Lists the in-cluster inference gateways in a global inference gateway,
26682
+ # in the order that they were added. Each summary includes the status of
26683
+ # the in-cluster inference gateway and, if the status is `FAILED`, the
26684
+ # reason for the failure. `DescribeGlobalInferenceGateway` doesn't
26685
+ # return the in-cluster inference gateways; use this operation to list
26686
+ # them.
26687
+ #
26688
+ # @option params [required, String] :identifier
26689
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
26690
+ # gateway.
26691
+ #
26692
+ # @option params [Array<Types::GlobalInferenceGatewayMemberFilter>] :filters
26693
+ # The filters to apply to the results. You can filter by `Status` and
26694
+ # `ClusterArn`. Multiple filters are combined with a logical AND.
26695
+ #
26696
+ # @option params [String] :next_token
26697
+ # If the result of the previous `ListInferenceGateways` request was
26698
+ # truncated, the response includes a `NextToken`. To retrieve the next
26699
+ # set of in-cluster inference gateways, use the token in the next
26700
+ # request.
26701
+ #
26702
+ # @option params [Integer] :max_results
26703
+ # The maximum number of in-cluster inference gateways to return in the
26704
+ # response.
26705
+ #
26706
+ # @return [Types::ListInferenceGatewaysResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
26707
+ #
26708
+ # * {Types::ListInferenceGatewaysResponse#inference_gateway_summaries #inference_gateway_summaries} => Array&lt;Types::GlobalInferenceGatewayMemberSummary&gt;
26709
+ # * {Types::ListInferenceGatewaysResponse#next_token #next_token} => String
26710
+ #
26711
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
26712
+ #
26713
+ # @example Request syntax with placeholder values
26714
+ #
26715
+ # resp = client.list_inference_gateways({
26716
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
26717
+ # filters: [
26718
+ # {
26719
+ # name: "Status", # required, accepts Status, ClusterArn
26720
+ # value: "GlobalInferenceGatewayMemberFilterValue", # required
26721
+ # },
26722
+ # ],
26723
+ # next_token: "GlobalInferenceGatewayNextToken",
26724
+ # max_results: 1,
26725
+ # })
26726
+ #
26727
+ # @example Response structure
26728
+ #
26729
+ # resp.inference_gateway_summaries #=> Array
26730
+ # resp.inference_gateway_summaries[0].name #=> String
26731
+ # resp.inference_gateway_summaries[0].namespace #=> String
26732
+ # resp.inference_gateway_summaries[0].cluster_arn #=> String
26733
+ # resp.inference_gateway_summaries[0].status #=> String, one of "ADDING", "ACTIVE", "REMOVING", "FAILED"
26734
+ # resp.inference_gateway_summaries[0].failure_reason #=> String
26735
+ # resp.next_token #=> String
26736
+ #
26737
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListInferenceGateways AWS API Documentation
26738
+ #
26739
+ # @overload list_inference_gateways(params = {})
26740
+ # @param [Hash] params ({})
26741
+ def list_inference_gateways(params = {}, options = {})
26742
+ req = build_request(:list_inference_gateways, params)
26743
+ req.send_request(options)
26744
+ end
26745
+
26115
26746
  # Returns a list of the subtasks for an Inference Recommender job.
26116
26747
  #
26117
26748
  # The supported subtasks are benchmarks, which evaluate the performance
@@ -28645,7 +29276,7 @@ module Aws::SageMaker
28645
29276
  # Filters the pipelines by who manages them. Specify `AWS` to return
28646
29277
  # pipelines that Amazon Web Services manages, or `CUSTOMER` to return
28647
29278
  # pipelines that you created. If you don't specify a value, the
28648
- # response includes both.
29279
+ # response includes only pipelines that you created.
28649
29280
  #
28650
29281
  # @return [Types::ListPipelinesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
28651
29282
  #
@@ -30117,6 +30748,135 @@ module Aws::SageMaker
30117
30748
  req.send_request(options)
30118
30749
  end
30119
30750
 
30751
+ # Moves running nodes from one instance group to another instance group.
30752
+ # The target instance group can be in the same HyperPod cluster or in a
30753
+ # different HyperPod cluster in the same account and Region. The
30754
+ # underlying instances aren't terminated.
30755
+ #
30756
+ # Each node keeps its instance ID, its `NodeLogicalId`, its network
30757
+ # interfaces and IP addresses, and its capacity. The node then joins the
30758
+ # target instance group with the target's configuration and lifecycle
30759
+ # scripts.
30760
+ #
30761
+ # The move replaces the node's root Amazon Elastic Block Store (Amazon
30762
+ # EBS) volume and secondary EBS volume, which deletes any data stored on
30763
+ # them. Back up any data that you need before you move the node.
30764
+ #
30765
+ # Specify the nodes to move with exactly one of `NodeIds`,
30766
+ # `NodeLogicalIds`, or `InstanceCount`. The operation is asynchronous
30767
+ # and returns after it accepts the nodes for the move. While a node
30768
+ # moves, its status is `DetachInProgress` and then `AttachInProgress`.
30769
+ # The node appears in the source cluster while it detaches. After
30770
+ # HyperPod hands the node off to the target instance group, the node
30771
+ # appears in the target cluster. To track the node, call
30772
+ # `DescribeClusterNode` or `ListClusterNodes` on the source or target
30773
+ # cluster.
30774
+ #
30775
+ # <note markdown="1"> Both clusters must be `InService`, use Amazon EKS orchestration, and
30776
+ # use `Continuous` as the `NodeProvisioningMode`.
30777
+ #
30778
+ # The source and target instance groups must also use compatible
30779
+ # configurations.
30780
+ #
30781
+ # </note>
30782
+ #
30783
+ # @option params [required, String] :source_cluster_arn
30784
+ # The Amazon Resource Name (ARN) of the HyperPod cluster that the nodes
30785
+ # are moved from.
30786
+ #
30787
+ # @option params [required, String] :source_instance_group_name
30788
+ # The name of the instance group in the source cluster that the nodes
30789
+ # are moved from.
30790
+ #
30791
+ # @option params [required, String] :target_cluster_arn
30792
+ # The Amazon Resource Name (ARN) of the HyperPod cluster that the nodes
30793
+ # are moved to. The target cluster must be in the same account and
30794
+ # Region as the source cluster, and can be the same cluster as the
30795
+ # source.
30796
+ #
30797
+ # @option params [required, String] :target_instance_group_name
30798
+ # The name of the instance group in the target cluster that the nodes
30799
+ # are moved to. If the target cluster is the same as the source cluster,
30800
+ # the target instance group must be different from the source instance
30801
+ # group.
30802
+ #
30803
+ # @option params [Integer] :instance_count
30804
+ # The number of nodes to move, from 1 to 50. HyperPod selects the nodes
30805
+ # from the source instance group. If fewer than this number of nodes are
30806
+ # eligible to move, the request fails and no nodes are moved. Specify
30807
+ # exactly one of `NodeIds`, `NodeLogicalIds`, or `InstanceCount`.
30808
+ #
30809
+ # @option params [Array<String>] :node_ids
30810
+ # A list of instance IDs of the nodes to move. You can specify up to 50
30811
+ # instance IDs. Each node is evaluated separately, so some nodes can be
30812
+ # moved while others fail. The request fails if moving the eligible
30813
+ # nodes would reduce the source instance group below its minimum
30814
+ # instance count. Specify exactly one of `NodeIds`, `NodeLogicalIds`, or
30815
+ # `InstanceCount`.
30816
+ #
30817
+ # @option params [Array<String>] :node_logical_ids
30818
+ # A list of `NodeLogicalIds` of the nodes to move. You can specify up to
30819
+ # 50 `NodeLogicalIds`. Each node is evaluated separately, so some nodes
30820
+ # can be moved while others fail. The request fails if moving the
30821
+ # eligible nodes would reduce the source instance group below its
30822
+ # minimum instance count. Specify exactly one of `NodeIds`,
30823
+ # `NodeLogicalIds`, or `InstanceCount`.
30824
+ #
30825
+ # @option params [String] :client_token
30826
+ # A unique, case-sensitive identifier that you provide to ensure that
30827
+ # the operation completes no more than one time. If you retry the
30828
+ # request with the same client token and the same parameters within 8
30829
+ # hours, the service returns the original response. It doesn't start a
30830
+ # new move. If you reuse a client token with different parameters, the
30831
+ # request fails.
30832
+ #
30833
+ # **A suitable default value is auto-generated.** You should normally
30834
+ # not need to pass this option.**
30835
+ #
30836
+ # @return [Types::MoveClusterNodesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
30837
+ #
30838
+ # * {Types::MoveClusterNodesResponse#successful #successful} => Array&lt;String&gt;
30839
+ # * {Types::MoveClusterNodesResponse#failed #failed} => Array&lt;Types::MoveClusterNodesError&gt;
30840
+ # * {Types::MoveClusterNodesResponse#successful_node_logical_ids #successful_node_logical_ids} => Array&lt;String&gt;
30841
+ # * {Types::MoveClusterNodesResponse#failed_node_logical_ids #failed_node_logical_ids} => Array&lt;Types::MoveClusterNodeLogicalIdsError&gt;
30842
+ #
30843
+ # @example Request syntax with placeholder values
30844
+ #
30845
+ # resp = client.move_cluster_nodes({
30846
+ # source_cluster_arn: "ClusterArn", # required
30847
+ # source_instance_group_name: "ClusterInstanceGroupName", # required
30848
+ # target_cluster_arn: "ClusterArn", # required
30849
+ # target_instance_group_name: "ClusterInstanceGroupName", # required
30850
+ # instance_count: 1,
30851
+ # node_ids: ["ClusterNodeId"],
30852
+ # node_logical_ids: ["ClusterNodeLogicalId"],
30853
+ # client_token: "MoveClusterNodesRequestClientTokenString",
30854
+ # })
30855
+ #
30856
+ # @example Response structure
30857
+ #
30858
+ # resp.successful #=> Array
30859
+ # resp.successful[0] #=> String
30860
+ # resp.failed #=> Array
30861
+ # resp.failed[0].code #=> String, one of "NodeIdNotFound", "InvalidNodeStatus", "NodeIdInUse", "NodeInstanceTypeMismatch"
30862
+ # resp.failed[0].message #=> String
30863
+ # resp.failed[0].node_id #=> String
30864
+ # resp.successful_node_logical_ids #=> Array
30865
+ # resp.successful_node_logical_ids[0] #=> String
30866
+ # resp.failed_node_logical_ids #=> Array
30867
+ # resp.failed_node_logical_ids[0].code #=> String, one of "NodeIdNotFound", "InvalidNodeStatus", "NodeIdInUse", "NodeInstanceTypeMismatch"
30868
+ # resp.failed_node_logical_ids[0].message #=> String
30869
+ # resp.failed_node_logical_ids[0].node_logical_id #=> String
30870
+ #
30871
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/MoveClusterNodes AWS API Documentation
30872
+ #
30873
+ # @overload move_cluster_nodes(params = {})
30874
+ # @param [Hash] params ({})
30875
+ def move_cluster_nodes(params = {}, options = {})
30876
+ req = build_request(:move_cluster_nodes, params)
30877
+ req.send_request(options)
30878
+ end
30879
+
30120
30880
  # Attaches a resource-based policy to an endpoint. With an endpoint
30121
30881
  # policy, you can allow other Amazon Web Services accounts to send
30122
30882
  # requests to your endpoint, or to inference components on it, through
@@ -30360,6 +31120,70 @@ module Aws::SageMaker
30360
31120
  req.send_request(options)
30361
31121
  end
30362
31122
 
31123
+ # Removes an in-cluster inference gateway from a global inference
31124
+ # gateway. This operation is asynchronous: the in-cluster inference
31125
+ # gateway moves to the `REMOVING` status, and then no longer appears in
31126
+ # `ListInferenceGateways`. If the in-cluster inference gateway isn't in
31127
+ # the global inference gateway, the operation succeeds and returns no
31128
+ # status. The operation returns `ResourceNotFound` only if the global
31129
+ # inference gateway doesn't exist.
31130
+ #
31131
+ # The operation fails with `ConflictException` while another operation
31132
+ # is in progress on the global inference gateway. It fails with
31133
+ # `ValidationException` if the in-cluster inference gateway is the last
31134
+ # one, because a global inference gateway must have at least one.
31135
+ #
31136
+ # @option params [required, String] :identifier
31137
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
31138
+ # gateway.
31139
+ #
31140
+ # @option params [required, String] :cluster_arn
31141
+ # The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster that
31142
+ # runs the in-cluster inference gateway.
31143
+ #
31144
+ # @option params [required, String] :namespace
31145
+ # The Kubernetes namespace of the in-cluster inference gateway.
31146
+ #
31147
+ # @option params [required, String] :name
31148
+ # The name of the `InferenceGatewayConfig` resource that defines the
31149
+ # in-cluster inference gateway.
31150
+ #
31151
+ # @return [Types::RemoveInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
31152
+ #
31153
+ # * {Types::RemoveInferenceGatewayResponse#arn #arn} => String
31154
+ # * {Types::RemoveInferenceGatewayResponse#id #id} => String
31155
+ # * {Types::RemoveInferenceGatewayResponse#name #name} => String
31156
+ # * {Types::RemoveInferenceGatewayResponse#gateway #gateway} => Types::GlobalInferenceGatewayMember
31157
+ # * {Types::RemoveInferenceGatewayResponse#status #status} => String
31158
+ #
31159
+ # @example Request syntax with placeholder values
31160
+ #
31161
+ # resp = client.remove_inference_gateway({
31162
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
31163
+ # cluster_arn: "GlobalInferenceGatewayClusterArn", # required
31164
+ # namespace: "GlobalInferenceGatewayKubernetesNamespace", # required
31165
+ # name: "GlobalInferenceGatewayKubernetesResourceName", # required
31166
+ # })
31167
+ #
31168
+ # @example Response structure
31169
+ #
31170
+ # resp.arn #=> String
31171
+ # resp.id #=> String
31172
+ # resp.name #=> String
31173
+ # resp.gateway.name #=> String
31174
+ # resp.gateway.namespace #=> String
31175
+ # resp.gateway.cluster_arn #=> String
31176
+ # resp.status #=> String, one of "ADDING", "ACTIVE", "REMOVING", "FAILED"
31177
+ #
31178
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/RemoveInferenceGateway AWS API Documentation
31179
+ #
31180
+ # @overload remove_inference_gateway(params = {})
31181
+ # @param [Hash] params ({})
31182
+ def remove_inference_gateway(params = {}, options = {})
31183
+ req = build_request(:remove_inference_gateway, params)
31184
+ req.send_request(options)
31185
+ end
31186
+
30363
31187
  # Renders the UI template so that you can preview the worker's
30364
31188
  # experience.
30365
31189
  #
@@ -33480,6 +34304,62 @@ module Aws::SageMaker
33480
34304
  req.send_request(options)
33481
34305
  end
33482
34306
 
34307
+ # Updates the routing configuration of a global inference gateway. To
34308
+ # add or remove in-cluster inference gateways, use `AddInferenceGateway`
34309
+ # and `RemoveInferenceGateway`. This operation is asynchronous: the
34310
+ # global inference gateway moves to the `UPDATING` status. The operation
34311
+ # fails with `ConflictException` while another operation is in progress
34312
+ # on the global inference gateway.
34313
+ #
34314
+ # @option params [required, String] :identifier
34315
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
34316
+ # gateway to update.
34317
+ #
34318
+ # @option params [required, Types::GlobalInferenceGatewayRouting] :routing
34319
+ # The new routing configuration of the global inference gateway.
34320
+ #
34321
+ # @return [Types::UpdateGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
34322
+ #
34323
+ # * {Types::UpdateGlobalInferenceGatewayResponse#arn #arn} => String
34324
+ # * {Types::UpdateGlobalInferenceGatewayResponse#id #id} => String
34325
+ # * {Types::UpdateGlobalInferenceGatewayResponse#name #name} => String
34326
+ # * {Types::UpdateGlobalInferenceGatewayResponse#status #status} => String
34327
+ # * {Types::UpdateGlobalInferenceGatewayResponse#routing #routing} => Types::GlobalInferenceGatewayRouting
34328
+ #
34329
+ # @example Request syntax with placeholder values
34330
+ #
34331
+ # resp = client.update_global_inference_gateway({
34332
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
34333
+ # routing: { # required
34334
+ # weights: { # required
34335
+ # kv_headroom: 1.0,
34336
+ # queue_depth: 1.0,
34337
+ # region_proximity: 1.0,
34338
+ # error_rate: 1.0,
34339
+ # },
34340
+ # },
34341
+ # })
34342
+ #
34343
+ # @example Response structure
34344
+ #
34345
+ # resp.arn #=> String
34346
+ # resp.id #=> String
34347
+ # resp.name #=> String
34348
+ # resp.status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
34349
+ # resp.routing.weights.kv_headroom #=> Float
34350
+ # resp.routing.weights.queue_depth #=> Float
34351
+ # resp.routing.weights.region_proximity #=> Float
34352
+ # resp.routing.weights.error_rate #=> Float
34353
+ #
34354
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/UpdateGlobalInferenceGateway AWS API Documentation
34355
+ #
34356
+ # @overload update_global_inference_gateway(params = {})
34357
+ # @param [Hash] params ({})
34358
+ def update_global_inference_gateway(params = {}, options = {})
34359
+ req = build_request(:update_global_inference_gateway, params)
34360
+ req.send_request(options)
34361
+ end
34362
+
33483
34363
  # Update a hub.
33484
34364
  #
33485
34365
  # @option params [required, String] :hub_name
@@ -36293,7 +37173,7 @@ module Aws::SageMaker
36293
37173
  tracer: tracer
36294
37174
  )
36295
37175
  context[:gem_name] = 'aws-sdk-sagemaker'
36296
- context[:gem_version] = '1.417.0'
37176
+ context[:gem_version] = '1.419.0'
36297
37177
  Seahorse::Client::Request.new(handlers, context)
36298
37178
  end
36299
37179