aws-sdk-sagemaker 1.417.0 → 1.418.0

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
@@ -15981,7 +16208,7 @@ module Aws::SageMaker
15981
16208
  # resp.node_details.instance_group_name #=> String
15982
16209
  # resp.node_details.instance_id #=> String
15983
16210
  # resp.node_details.node_logical_id #=> String
15984
- # resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound"
16211
+ # resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound", "DetachInProgress", "AttachInProgress"
15985
16212
  # resp.node_details.instance_status.message #=> String
15986
16213
  # 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
16214
  # resp.node_details.launch_time #=> Time
@@ -17764,6 +17991,60 @@ module Aws::SageMaker
17764
17991
  req.send_request(options)
17765
17992
  end
17766
17993
 
17994
+ # Retrieves information about a global inference gateway, including its
17995
+ # status, endpoints, and routing configuration. To list the in-cluster
17996
+ # inference gateways of the global inference gateway, use
17997
+ # `ListInferenceGateways`. To read the tags of the global inference
17998
+ # gateway, use `ListTags`.
17999
+ #
18000
+ # @option params [required, String] :identifier
18001
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
18002
+ # gateway.
18003
+ #
18004
+ # @return [Types::DescribeGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
18005
+ #
18006
+ # * {Types::DescribeGlobalInferenceGatewayResponse#arn #arn} => String
18007
+ # * {Types::DescribeGlobalInferenceGatewayResponse#id #id} => String
18008
+ # * {Types::DescribeGlobalInferenceGatewayResponse#name #name} => String
18009
+ # * {Types::DescribeGlobalInferenceGatewayResponse#execution_role_arn #execution_role_arn} => String
18010
+ # * {Types::DescribeGlobalInferenceGatewayResponse#status #status} => String
18011
+ # * {Types::DescribeGlobalInferenceGatewayResponse#endpoint_url #endpoint_url} => String
18012
+ # * {Types::DescribeGlobalInferenceGatewayResponse#vpc_endpoint_service_name #vpc_endpoint_service_name} => String
18013
+ # * {Types::DescribeGlobalInferenceGatewayResponse#routing #routing} => Types::GlobalInferenceGatewayRouting
18014
+ # * {Types::DescribeGlobalInferenceGatewayResponse#creation_time #creation_time} => Time
18015
+ # * {Types::DescribeGlobalInferenceGatewayResponse#failure_reason #failure_reason} => String
18016
+ #
18017
+ # @example Request syntax with placeholder values
18018
+ #
18019
+ # resp = client.describe_global_inference_gateway({
18020
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
18021
+ # })
18022
+ #
18023
+ # @example Response structure
18024
+ #
18025
+ # resp.arn #=> String
18026
+ # resp.id #=> String
18027
+ # resp.name #=> String
18028
+ # resp.execution_role_arn #=> String
18029
+ # resp.status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
18030
+ # resp.endpoint_url #=> String
18031
+ # resp.vpc_endpoint_service_name #=> String
18032
+ # resp.routing.weights.kv_headroom #=> Float
18033
+ # resp.routing.weights.queue_depth #=> Float
18034
+ # resp.routing.weights.region_proximity #=> Float
18035
+ # resp.routing.weights.error_rate #=> Float
18036
+ # resp.creation_time #=> Time
18037
+ # resp.failure_reason #=> String
18038
+ #
18039
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeGlobalInferenceGateway AWS API Documentation
18040
+ #
18041
+ # @overload describe_global_inference_gateway(params = {})
18042
+ # @param [Hash] params ({})
18043
+ def describe_global_inference_gateway(params = {}, options = {})
18044
+ req = build_request(:describe_global_inference_gateway, params)
18045
+ req.send_request(options)
18046
+ end
18047
+
17767
18048
  # Describes a hub.
17768
18049
  #
17769
18050
  # @option params [required, String] :hub_name
@@ -23943,7 +24224,7 @@ module Aws::SageMaker
23943
24224
  # 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
24225
  # resp.cluster_node_summaries[0].launch_time #=> Time
23945
24226
  # 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"
24227
+ # resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress", "NotFound", "DetachInProgress", "AttachInProgress"
23947
24228
  # resp.cluster_node_summaries[0].instance_status.message #=> String
23948
24229
  # resp.cluster_node_summaries[0].ultra_server_info.id #=> String
23949
24230
  # resp.cluster_node_summaries[0].ultra_server_info.type #=> String
@@ -25356,6 +25637,62 @@ module Aws::SageMaker
25356
25637
  req.send_request(options)
25357
25638
  end
25358
25639
 
25640
+ # Lists summaries of the global inference gateways in your account. You
25641
+ # can filter the results by status.
25642
+ #
25643
+ # @option params [Array<Types::GlobalInferenceGatewayFilter>] :filters
25644
+ # The filters to apply to the results. You can filter by `Status`.
25645
+ # Multiple filters are combined with a logical AND.
25646
+ #
25647
+ # @option params [String] :next_token
25648
+ # If the result of the previous `ListGlobalInferenceGateways` request
25649
+ # was truncated, the response includes a `NextToken`. To retrieve the
25650
+ # next set of global inference gateways, use the token in the next
25651
+ # request.
25652
+ #
25653
+ # @option params [Integer] :max_results
25654
+ # The maximum number of global inference gateways to return in the
25655
+ # response.
25656
+ #
25657
+ # @return [Types::ListGlobalInferenceGatewaysResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
25658
+ #
25659
+ # * {Types::ListGlobalInferenceGatewaysResponse#global_inference_gateway_summaries #global_inference_gateway_summaries} => Array&lt;Types::GlobalInferenceGatewaySummary&gt;
25660
+ # * {Types::ListGlobalInferenceGatewaysResponse#next_token #next_token} => String
25661
+ #
25662
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
25663
+ #
25664
+ # @example Request syntax with placeholder values
25665
+ #
25666
+ # resp = client.list_global_inference_gateways({
25667
+ # filters: [
25668
+ # {
25669
+ # name: "Status", # required, accepts Status
25670
+ # value: "GlobalInferenceGatewayFilterValue", # required
25671
+ # },
25672
+ # ],
25673
+ # next_token: "GlobalInferenceGatewayNextToken",
25674
+ # max_results: 1,
25675
+ # })
25676
+ #
25677
+ # @example Response structure
25678
+ #
25679
+ # resp.global_inference_gateway_summaries #=> Array
25680
+ # resp.global_inference_gateway_summaries[0].arn #=> String
25681
+ # resp.global_inference_gateway_summaries[0].id #=> String
25682
+ # resp.global_inference_gateway_summaries[0].name #=> String
25683
+ # resp.global_inference_gateway_summaries[0].status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
25684
+ # resp.global_inference_gateway_summaries[0].creation_time #=> Time
25685
+ # resp.next_token #=> String
25686
+ #
25687
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListGlobalInferenceGateways AWS API Documentation
25688
+ #
25689
+ # @overload list_global_inference_gateways(params = {})
25690
+ # @param [Hash] params ({})
25691
+ def list_global_inference_gateways(params = {}, options = {})
25692
+ req = build_request(:list_global_inference_gateways, params)
25693
+ req.send_request(options)
25694
+ end
25695
+
25359
25696
  # List hub content versions.
25360
25697
  #
25361
25698
  # @option params [required, String] :hub_name
@@ -26112,6 +26449,71 @@ module Aws::SageMaker
26112
26449
  req.send_request(options)
26113
26450
  end
26114
26451
 
26452
+ # Lists the in-cluster inference gateways in a global inference gateway,
26453
+ # in the order that they were added. Each summary includes the status of
26454
+ # the in-cluster inference gateway and, if the status is `FAILED`, the
26455
+ # reason for the failure. `DescribeGlobalInferenceGateway` doesn't
26456
+ # return the in-cluster inference gateways; use this operation to list
26457
+ # them.
26458
+ #
26459
+ # @option params [required, String] :identifier
26460
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
26461
+ # gateway.
26462
+ #
26463
+ # @option params [Array<Types::GlobalInferenceGatewayMemberFilter>] :filters
26464
+ # The filters to apply to the results. You can filter by `Status` and
26465
+ # `ClusterArn`. Multiple filters are combined with a logical AND.
26466
+ #
26467
+ # @option params [String] :next_token
26468
+ # If the result of the previous `ListInferenceGateways` request was
26469
+ # truncated, the response includes a `NextToken`. To retrieve the next
26470
+ # set of in-cluster inference gateways, use the token in the next
26471
+ # request.
26472
+ #
26473
+ # @option params [Integer] :max_results
26474
+ # The maximum number of in-cluster inference gateways to return in the
26475
+ # response.
26476
+ #
26477
+ # @return [Types::ListInferenceGatewaysResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
26478
+ #
26479
+ # * {Types::ListInferenceGatewaysResponse#inference_gateway_summaries #inference_gateway_summaries} => Array&lt;Types::GlobalInferenceGatewayMemberSummary&gt;
26480
+ # * {Types::ListInferenceGatewaysResponse#next_token #next_token} => String
26481
+ #
26482
+ # The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
26483
+ #
26484
+ # @example Request syntax with placeholder values
26485
+ #
26486
+ # resp = client.list_inference_gateways({
26487
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
26488
+ # filters: [
26489
+ # {
26490
+ # name: "Status", # required, accepts Status, ClusterArn
26491
+ # value: "GlobalInferenceGatewayMemberFilterValue", # required
26492
+ # },
26493
+ # ],
26494
+ # next_token: "GlobalInferenceGatewayNextToken",
26495
+ # max_results: 1,
26496
+ # })
26497
+ #
26498
+ # @example Response structure
26499
+ #
26500
+ # resp.inference_gateway_summaries #=> Array
26501
+ # resp.inference_gateway_summaries[0].name #=> String
26502
+ # resp.inference_gateway_summaries[0].namespace #=> String
26503
+ # resp.inference_gateway_summaries[0].cluster_arn #=> String
26504
+ # resp.inference_gateway_summaries[0].status #=> String, one of "ADDING", "ACTIVE", "REMOVING", "FAILED"
26505
+ # resp.inference_gateway_summaries[0].failure_reason #=> String
26506
+ # resp.next_token #=> String
26507
+ #
26508
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListInferenceGateways AWS API Documentation
26509
+ #
26510
+ # @overload list_inference_gateways(params = {})
26511
+ # @param [Hash] params ({})
26512
+ def list_inference_gateways(params = {}, options = {})
26513
+ req = build_request(:list_inference_gateways, params)
26514
+ req.send_request(options)
26515
+ end
26516
+
26115
26517
  # Returns a list of the subtasks for an Inference Recommender job.
26116
26518
  #
26117
26519
  # The supported subtasks are benchmarks, which evaluate the performance
@@ -28645,7 +29047,7 @@ module Aws::SageMaker
28645
29047
  # Filters the pipelines by who manages them. Specify `AWS` to return
28646
29048
  # pipelines that Amazon Web Services manages, or `CUSTOMER` to return
28647
29049
  # pipelines that you created. If you don't specify a value, the
28648
- # response includes both.
29050
+ # response includes only pipelines that you created.
28649
29051
  #
28650
29052
  # @return [Types::ListPipelinesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
28651
29053
  #
@@ -30117,6 +30519,135 @@ module Aws::SageMaker
30117
30519
  req.send_request(options)
30118
30520
  end
30119
30521
 
30522
+ # Moves running nodes from one instance group to another instance group.
30523
+ # The target instance group can be in the same HyperPod cluster or in a
30524
+ # different HyperPod cluster in the same account and Region. The
30525
+ # underlying instances aren't terminated.
30526
+ #
30527
+ # Each node keeps its instance ID, its `NodeLogicalId`, its network
30528
+ # interfaces and IP addresses, and its capacity. The node then joins the
30529
+ # target instance group with the target's configuration and lifecycle
30530
+ # scripts.
30531
+ #
30532
+ # The move replaces the node's root Amazon Elastic Block Store (Amazon
30533
+ # EBS) volume and secondary EBS volume, which deletes any data stored on
30534
+ # them. Back up any data that you need before you move the node.
30535
+ #
30536
+ # Specify the nodes to move with exactly one of `NodeIds`,
30537
+ # `NodeLogicalIds`, or `InstanceCount`. The operation is asynchronous
30538
+ # and returns after it accepts the nodes for the move. While a node
30539
+ # moves, its status is `DetachInProgress` and then `AttachInProgress`.
30540
+ # The node appears in the source cluster while it detaches. After
30541
+ # HyperPod hands the node off to the target instance group, the node
30542
+ # appears in the target cluster. To track the node, call
30543
+ # `DescribeClusterNode` or `ListClusterNodes` on the source or target
30544
+ # cluster.
30545
+ #
30546
+ # <note markdown="1"> Both clusters must be `InService`, use Amazon EKS orchestration, and
30547
+ # use `Continuous` as the `NodeProvisioningMode`.
30548
+ #
30549
+ # The source and target instance groups must also use compatible
30550
+ # configurations.
30551
+ #
30552
+ # </note>
30553
+ #
30554
+ # @option params [required, String] :source_cluster_arn
30555
+ # The Amazon Resource Name (ARN) of the HyperPod cluster that the nodes
30556
+ # are moved from.
30557
+ #
30558
+ # @option params [required, String] :source_instance_group_name
30559
+ # The name of the instance group in the source cluster that the nodes
30560
+ # are moved from.
30561
+ #
30562
+ # @option params [required, String] :target_cluster_arn
30563
+ # The Amazon Resource Name (ARN) of the HyperPod cluster that the nodes
30564
+ # are moved to. The target cluster must be in the same account and
30565
+ # Region as the source cluster, and can be the same cluster as the
30566
+ # source.
30567
+ #
30568
+ # @option params [required, String] :target_instance_group_name
30569
+ # The name of the instance group in the target cluster that the nodes
30570
+ # are moved to. If the target cluster is the same as the source cluster,
30571
+ # the target instance group must be different from the source instance
30572
+ # group.
30573
+ #
30574
+ # @option params [Integer] :instance_count
30575
+ # The number of nodes to move, from 1 to 50. HyperPod selects the nodes
30576
+ # from the source instance group. If fewer than this number of nodes are
30577
+ # eligible to move, the request fails and no nodes are moved. Specify
30578
+ # exactly one of `NodeIds`, `NodeLogicalIds`, or `InstanceCount`.
30579
+ #
30580
+ # @option params [Array<String>] :node_ids
30581
+ # A list of instance IDs of the nodes to move. You can specify up to 50
30582
+ # instance IDs. Each node is evaluated separately, so some nodes can be
30583
+ # moved while others fail. The request fails if moving the eligible
30584
+ # nodes would reduce the source instance group below its minimum
30585
+ # instance count. Specify exactly one of `NodeIds`, `NodeLogicalIds`, or
30586
+ # `InstanceCount`.
30587
+ #
30588
+ # @option params [Array<String>] :node_logical_ids
30589
+ # A list of `NodeLogicalIds` of the nodes to move. You can specify up to
30590
+ # 50 `NodeLogicalIds`. Each node is evaluated separately, so some nodes
30591
+ # can be moved while others fail. The request fails if moving the
30592
+ # eligible nodes would reduce the source instance group below its
30593
+ # minimum instance count. Specify exactly one of `NodeIds`,
30594
+ # `NodeLogicalIds`, or `InstanceCount`.
30595
+ #
30596
+ # @option params [String] :client_token
30597
+ # A unique, case-sensitive identifier that you provide to ensure that
30598
+ # the operation completes no more than one time. If you retry the
30599
+ # request with the same client token and the same parameters within 8
30600
+ # hours, the service returns the original response. It doesn't start a
30601
+ # new move. If you reuse a client token with different parameters, the
30602
+ # request fails.
30603
+ #
30604
+ # **A suitable default value is auto-generated.** You should normally
30605
+ # not need to pass this option.**
30606
+ #
30607
+ # @return [Types::MoveClusterNodesResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
30608
+ #
30609
+ # * {Types::MoveClusterNodesResponse#successful #successful} => Array&lt;String&gt;
30610
+ # * {Types::MoveClusterNodesResponse#failed #failed} => Array&lt;Types::MoveClusterNodesError&gt;
30611
+ # * {Types::MoveClusterNodesResponse#successful_node_logical_ids #successful_node_logical_ids} => Array&lt;String&gt;
30612
+ # * {Types::MoveClusterNodesResponse#failed_node_logical_ids #failed_node_logical_ids} => Array&lt;Types::MoveClusterNodeLogicalIdsError&gt;
30613
+ #
30614
+ # @example Request syntax with placeholder values
30615
+ #
30616
+ # resp = client.move_cluster_nodes({
30617
+ # source_cluster_arn: "ClusterArn", # required
30618
+ # source_instance_group_name: "ClusterInstanceGroupName", # required
30619
+ # target_cluster_arn: "ClusterArn", # required
30620
+ # target_instance_group_name: "ClusterInstanceGroupName", # required
30621
+ # instance_count: 1,
30622
+ # node_ids: ["ClusterNodeId"],
30623
+ # node_logical_ids: ["ClusterNodeLogicalId"],
30624
+ # client_token: "MoveClusterNodesRequestClientTokenString",
30625
+ # })
30626
+ #
30627
+ # @example Response structure
30628
+ #
30629
+ # resp.successful #=> Array
30630
+ # resp.successful[0] #=> String
30631
+ # resp.failed #=> Array
30632
+ # resp.failed[0].code #=> String, one of "NodeIdNotFound", "InvalidNodeStatus", "NodeIdInUse", "NodeInstanceTypeMismatch"
30633
+ # resp.failed[0].message #=> String
30634
+ # resp.failed[0].node_id #=> String
30635
+ # resp.successful_node_logical_ids #=> Array
30636
+ # resp.successful_node_logical_ids[0] #=> String
30637
+ # resp.failed_node_logical_ids #=> Array
30638
+ # resp.failed_node_logical_ids[0].code #=> String, one of "NodeIdNotFound", "InvalidNodeStatus", "NodeIdInUse", "NodeInstanceTypeMismatch"
30639
+ # resp.failed_node_logical_ids[0].message #=> String
30640
+ # resp.failed_node_logical_ids[0].node_logical_id #=> String
30641
+ #
30642
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/MoveClusterNodes AWS API Documentation
30643
+ #
30644
+ # @overload move_cluster_nodes(params = {})
30645
+ # @param [Hash] params ({})
30646
+ def move_cluster_nodes(params = {}, options = {})
30647
+ req = build_request(:move_cluster_nodes, params)
30648
+ req.send_request(options)
30649
+ end
30650
+
30120
30651
  # Attaches a resource-based policy to an endpoint. With an endpoint
30121
30652
  # policy, you can allow other Amazon Web Services accounts to send
30122
30653
  # requests to your endpoint, or to inference components on it, through
@@ -30360,6 +30891,70 @@ module Aws::SageMaker
30360
30891
  req.send_request(options)
30361
30892
  end
30362
30893
 
30894
+ # Removes an in-cluster inference gateway from a global inference
30895
+ # gateway. This operation is asynchronous: the in-cluster inference
30896
+ # gateway moves to the `REMOVING` status, and then no longer appears in
30897
+ # `ListInferenceGateways`. If the in-cluster inference gateway isn't in
30898
+ # the global inference gateway, the operation succeeds and returns no
30899
+ # status. The operation returns `ResourceNotFound` only if the global
30900
+ # inference gateway doesn't exist.
30901
+ #
30902
+ # The operation fails with `ConflictException` while another operation
30903
+ # is in progress on the global inference gateway. It fails with
30904
+ # `ValidationException` if the in-cluster inference gateway is the last
30905
+ # one, because a global inference gateway must have at least one.
30906
+ #
30907
+ # @option params [required, String] :identifier
30908
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
30909
+ # gateway.
30910
+ #
30911
+ # @option params [required, String] :cluster_arn
30912
+ # The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster that
30913
+ # runs the in-cluster inference gateway.
30914
+ #
30915
+ # @option params [required, String] :namespace
30916
+ # The Kubernetes namespace of the in-cluster inference gateway.
30917
+ #
30918
+ # @option params [required, String] :name
30919
+ # The name of the `InferenceGatewayConfig` resource that defines the
30920
+ # in-cluster inference gateway.
30921
+ #
30922
+ # @return [Types::RemoveInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
30923
+ #
30924
+ # * {Types::RemoveInferenceGatewayResponse#arn #arn} => String
30925
+ # * {Types::RemoveInferenceGatewayResponse#id #id} => String
30926
+ # * {Types::RemoveInferenceGatewayResponse#name #name} => String
30927
+ # * {Types::RemoveInferenceGatewayResponse#gateway #gateway} => Types::GlobalInferenceGatewayMember
30928
+ # * {Types::RemoveInferenceGatewayResponse#status #status} => String
30929
+ #
30930
+ # @example Request syntax with placeholder values
30931
+ #
30932
+ # resp = client.remove_inference_gateway({
30933
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
30934
+ # cluster_arn: "GlobalInferenceGatewayClusterArn", # required
30935
+ # namespace: "GlobalInferenceGatewayKubernetesNamespace", # required
30936
+ # name: "GlobalInferenceGatewayKubernetesResourceName", # required
30937
+ # })
30938
+ #
30939
+ # @example Response structure
30940
+ #
30941
+ # resp.arn #=> String
30942
+ # resp.id #=> String
30943
+ # resp.name #=> String
30944
+ # resp.gateway.name #=> String
30945
+ # resp.gateway.namespace #=> String
30946
+ # resp.gateway.cluster_arn #=> String
30947
+ # resp.status #=> String, one of "ADDING", "ACTIVE", "REMOVING", "FAILED"
30948
+ #
30949
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/RemoveInferenceGateway AWS API Documentation
30950
+ #
30951
+ # @overload remove_inference_gateway(params = {})
30952
+ # @param [Hash] params ({})
30953
+ def remove_inference_gateway(params = {}, options = {})
30954
+ req = build_request(:remove_inference_gateway, params)
30955
+ req.send_request(options)
30956
+ end
30957
+
30363
30958
  # Renders the UI template so that you can preview the worker's
30364
30959
  # experience.
30365
30960
  #
@@ -33480,6 +34075,62 @@ module Aws::SageMaker
33480
34075
  req.send_request(options)
33481
34076
  end
33482
34077
 
34078
+ # Updates the routing configuration of a global inference gateway. To
34079
+ # add or remove in-cluster inference gateways, use `AddInferenceGateway`
34080
+ # and `RemoveInferenceGateway`. This operation is asynchronous: the
34081
+ # global inference gateway moves to the `UPDATING` status. The operation
34082
+ # fails with `ConflictException` while another operation is in progress
34083
+ # on the global inference gateway.
34084
+ #
34085
+ # @option params [required, String] :identifier
34086
+ # The name, Amazon Resource Name (ARN), or ID of the global inference
34087
+ # gateway to update.
34088
+ #
34089
+ # @option params [required, Types::GlobalInferenceGatewayRouting] :routing
34090
+ # The new routing configuration of the global inference gateway.
34091
+ #
34092
+ # @return [Types::UpdateGlobalInferenceGatewayResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
34093
+ #
34094
+ # * {Types::UpdateGlobalInferenceGatewayResponse#arn #arn} => String
34095
+ # * {Types::UpdateGlobalInferenceGatewayResponse#id #id} => String
34096
+ # * {Types::UpdateGlobalInferenceGatewayResponse#name #name} => String
34097
+ # * {Types::UpdateGlobalInferenceGatewayResponse#status #status} => String
34098
+ # * {Types::UpdateGlobalInferenceGatewayResponse#routing #routing} => Types::GlobalInferenceGatewayRouting
34099
+ #
34100
+ # @example Request syntax with placeholder values
34101
+ #
34102
+ # resp = client.update_global_inference_gateway({
34103
+ # identifier: "GlobalInferenceGatewayIdentifier", # required
34104
+ # routing: { # required
34105
+ # weights: { # required
34106
+ # kv_headroom: 1.0,
34107
+ # queue_depth: 1.0,
34108
+ # region_proximity: 1.0,
34109
+ # error_rate: 1.0,
34110
+ # },
34111
+ # },
34112
+ # })
34113
+ #
34114
+ # @example Response structure
34115
+ #
34116
+ # resp.arn #=> String
34117
+ # resp.id #=> String
34118
+ # resp.name #=> String
34119
+ # resp.status #=> String, one of "CREATING", "ACTIVE", "UPDATING", "DELETING", "FAILED"
34120
+ # resp.routing.weights.kv_headroom #=> Float
34121
+ # resp.routing.weights.queue_depth #=> Float
34122
+ # resp.routing.weights.region_proximity #=> Float
34123
+ # resp.routing.weights.error_rate #=> Float
34124
+ #
34125
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/UpdateGlobalInferenceGateway AWS API Documentation
34126
+ #
34127
+ # @overload update_global_inference_gateway(params = {})
34128
+ # @param [Hash] params ({})
34129
+ def update_global_inference_gateway(params = {}, options = {})
34130
+ req = build_request(:update_global_inference_gateway, params)
34131
+ req.send_request(options)
34132
+ end
34133
+
33483
34134
  # Update a hub.
33484
34135
  #
33485
34136
  # @option params [required, String] :hub_name
@@ -36293,7 +36944,7 @@ module Aws::SageMaker
36293
36944
  tracer: tracer
36294
36945
  )
36295
36946
  context[:gem_name] = 'aws-sdk-sagemaker'
36296
- context[:gem_version] = '1.417.0'
36947
+ context[:gem_version] = '1.418.0'
36297
36948
  Seahorse::Client::Request.new(handlers, context)
36298
36949
  end
36299
36950