feat(client-application-auto-scaling): Amazon SageMaker customers can now use Application Auto Scaling to automatically scale the number of Inference Component copies across an endpoint to meet the varying demand of their workloads.

Author: awstools

clients/client-application-auto-scaling/README.md

@@ -49,6 +49,9 @@ resources:</p>
 <p>Amazon SageMaker Serverless endpoint provisioned concurrency</p>
 </li>
 <li>
+<p>Amazon SageMaker inference components</p>
+</li>
+<li>
 <p>Spot Fleets (Amazon EC2)</p>
 </li>
 <li>

clients/client-application-auto-scaling/src/ApplicationAutoScaling.ts

@@ -337,6 +337,9 @@ export interface ApplicationAutoScaling {
  *                <p>Amazon SageMaker Serverless endpoint provisioned concurrency</p>
  *             </li>
  *             <li>
+ *                <p>Amazon SageMaker inference components</p>
+ *             </li>
+ *             <li>
  *                <p>Spot Fleets (Amazon EC2)</p>
  *             </li>
  *             <li>

clients/client-application-auto-scaling/src/ApplicationAutoScalingClient.ts

@@ -352,6 +352,9 @@ export interface ApplicationAutoScalingClientResolvedConfig extends ApplicationA
  *                <p>Amazon SageMaker Serverless endpoint provisioned concurrency</p>
  *             </li>
  *             <li>
+ *                <p>Amazon SageMaker inference components</p>
+ *             </li>
+ *             <li>
  *                <p>Spot Fleets (Amazon EC2)</p>
  *             </li>
  *             <li>

clients/client-application-auto-scaling/src/commands/DeleteScalingPolicyCommand.ts

@@ -45,7 +45,7 @@ export interface DeleteScalingPolicyCommandOutput extends DeleteScalingPolicyRes
  *          <p>Deleting a step scaling policy deletes the underlying alarm action, but does not delete
  *          the CloudWatch alarm associated with the scaling policy, even if it no longer has an associated
  *          action.</p>
- *          <p>For more information, see <a href="https://docs.aws.amazon.com/autoscaling/application/userguide/application-auto-scaling-step-scaling-policies.html#delete-step-scaling-policy">Delete a step scaling policy</a> and <a href="https://docs.aws.amazon.com/autoscaling/application/userguide/application-auto-scaling-target-tracking.html#delete-target-tracking-policy">Delete a target tracking scaling policy</a> in the
+ *          <p>For more information, see <a href="https://docs.aws.amazon.com/autoscaling/application/userguide/create-step-scaling-policy-cli.html#delete-step-scaling-policy">Delete a step scaling policy</a> and <a href="https://docs.aws.amazon.com/autoscaling/application/userguide/create-target-tracking-policy-cli.html#delete-target-tracking-policy">Delete a target tracking scaling policy</a> in the
  *             <i>Application Auto Scaling User Guide</i>.</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
@@ -57,7 +57,7 @@ export interface DeleteScalingPolicyCommandOutput extends DeleteScalingPolicyRes
  *   PolicyName: "STRING_VALUE", // required
  *   ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  *   ResourceId: "STRING_VALUE", // required
- *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency", // required
+ *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount", // required
  * };
  * const command = new DeleteScalingPolicyCommand(input);
  * const response = await client.send(command);

clients/client-application-auto-scaling/src/commands/DeleteScheduledActionCommand.ts

@@ -53,7 +53,7 @@ export interface DeleteScheduledActionCommandOutput extends DeleteScheduledActio
  *   ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  *   ScheduledActionName: "STRING_VALUE", // required
  *   ResourceId: "STRING_VALUE", // required
- *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency", // required
+ *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount", // required
  * };
  * const command = new DeleteScheduledActionCommand(input);
  * const response = await client.send(command);

clients/client-application-auto-scaling/src/commands/DeregisterScalableTargetCommand.ts

@@ -56,7 +56,7 @@ export interface DeregisterScalableTargetCommandOutput extends DeregisterScalabl
  * const input = { // DeregisterScalableTargetRequest
  *   ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  *   ResourceId: "STRING_VALUE", // required
- *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency", // required
+ *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount", // required
  * };
  * const command = new DeregisterScalableTargetCommand(input);
  * const response = await client.send(command);

clients/client-application-auto-scaling/src/commands/DescribeScalableTargetsCommand.ts

@@ -55,7 +55,7 @@ export interface DescribeScalableTargetsCommandOutput extends DescribeScalableTa
  *   ResourceIds: [ // ResourceIdsMaxLen1600
  *     "STRING_VALUE",
  *   ],
- *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency",
+ *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount",
  *   MaxResults: Number("int"),
  *   NextToken: "STRING_VALUE",
  * };
@@ -66,7 +66,7 @@ export interface DescribeScalableTargetsCommandOutput extends DescribeScalableTa
  * //     { // ScalableTarget
  * //       ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  * //       ResourceId: "STRING_VALUE", // required
- * //       ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency", // required
+ * //       ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount", // required
  * //       MinCapacity: Number("int"), // required
  * //       MaxCapacity: Number("int"), // required
  * //       RoleARN: "STRING_VALUE", // required

clients/client-application-auto-scaling/src/commands/DescribeScalingActivitiesCommand.ts

@@ -55,7 +55,7 @@ export interface DescribeScalingActivitiesCommandOutput extends DescribeScalingA
  * const input = { // DescribeScalingActivitiesRequest
  *   ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  *   ResourceId: "STRING_VALUE",
- *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency",
+ *   ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount",
  *   MaxResults: Number("int"),
  *   NextToken: "STRING_VALUE",
  *   IncludeNotScaledActivities: true || false,
@@ -68,7 +68,7 @@ export interface DescribeScalingActivitiesCommandOutput extends DescribeScalingA
  * //       ActivityId: "STRING_VALUE", // required
  * //       ServiceNamespace: "ecs" || "elasticmapreduce" || "ec2" || "appstream" || "dynamodb" || "rds" || "sagemaker" || "custom-resource" || "comprehend" || "lambda" || "cassandra" || "kafka" || "elasticache" || "neptune", // required
  * //       ResourceId: "STRING_VALUE", // required
- * //       ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency", // required
+ * //       ScalableDimension: "ecs:service:DesiredCount" || "ec2:spot-fleet-request:TargetCapacity" || "elasticmapreduce:instancegroup:InstanceCount" || "appstream:fleet:DesiredCapacity" || "dynamodb:table:ReadCapacityUnits" || "dynamodb:table:WriteCapacityUnits" || "dynamodb:index:ReadCapacityUnits" || "dynamodb:index:WriteCapacityUnits" || "rds:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredInstanceCount" || "custom-resource:ResourceType:Property" || "comprehend:document-classifier-endpoint:DesiredInferenceUnits" || "comprehend:entity-recognizer-endpoint:DesiredInferenceUnits" || "lambda:function:ProvisionedConcurrency" || "cassandra:table:ReadCapacityUnits" || "cassandra:table:WriteCapacityUnits" || "kafka:broker-storage:VolumeSize" || "elasticache:replication-group:NodeGroups" || "elasticache:replication-group:Replicas" || "neptune:cluster:ReadReplicaCount" || "sagemaker:variant:DesiredProvisionedConcurrency" || "sagemaker:inference-component:DesiredCopyCount", // required
  * //       Description: "STRING_VALUE", // required
  * //       Cause: "STRING_VALUE", // required
  * //       StartTime: new Date("TIMESTAMP"), // required