|
8313 | 8313 | "min":0,
|
8314 | 8314 | "pattern":"arn:aws[a-z\\-]*:sagemaker:[a-z0-9\\-]*:[0-9]{12}:cluster/[a-z0-9]{12}"
|
8315 | 8315 | },
|
| 8316 | + "ClusterAutoScalerType":{ |
| 8317 | + "type":"string", |
| 8318 | + "enum":["Karpenter"] |
| 8319 | + }, |
| 8320 | + "ClusterAutoScalingConfig":{ |
| 8321 | + "type":"structure", |
| 8322 | + "required":["Mode"], |
| 8323 | + "members":{ |
| 8324 | + "Mode":{ |
| 8325 | + "shape":"ClusterAutoScalingMode", |
| 8326 | + "documentation":"<p>Describes whether autoscaling is enabled or disabled for the cluster. Valid values are <code>Enable</code> and <code>Disable</code>.</p>" |
| 8327 | + }, |
| 8328 | + "AutoScalerType":{ |
| 8329 | + "shape":"ClusterAutoScalerType", |
| 8330 | + "documentation":"<p>The type of autoscaler to use. Currently supported value is <code>Karpenter</code>.</p>" |
| 8331 | + } |
| 8332 | + }, |
| 8333 | + "documentation":"<p>Specifies the autoscaling configuration for a HyperPod cluster.</p>" |
| 8334 | + }, |
| 8335 | + "ClusterAutoScalingConfigOutput":{ |
| 8336 | + "type":"structure", |
| 8337 | + "required":[ |
| 8338 | + "Mode", |
| 8339 | + "Status" |
| 8340 | + ], |
| 8341 | + "members":{ |
| 8342 | + "Mode":{ |
| 8343 | + "shape":"ClusterAutoScalingMode", |
| 8344 | + "documentation":"<p>Describes whether autoscaling is enabled or disabled for the cluster.</p>" |
| 8345 | + }, |
| 8346 | + "AutoScalerType":{ |
| 8347 | + "shape":"ClusterAutoScalerType", |
| 8348 | + "documentation":"<p>The type of autoscaler configured for the cluster.</p>" |
| 8349 | + }, |
| 8350 | + "Status":{ |
| 8351 | + "shape":"ClusterAutoScalingStatus", |
| 8352 | + "documentation":"<p>The current status of the autoscaling configuration. Valid values are <code>InService</code>, <code>Failed</code>, <code>Creating</code>, and <code>Deleting</code>.</p>" |
| 8353 | + }, |
| 8354 | + "FailureMessage":{ |
| 8355 | + "shape":"String", |
| 8356 | + "documentation":"<p>If the autoscaling status is <code>Failed</code>, this field contains a message describing the failure.</p>" |
| 8357 | + } |
| 8358 | + }, |
| 8359 | + "documentation":"<p>The autoscaling configuration and status information for a HyperPod cluster.</p>" |
| 8360 | + }, |
| 8361 | + "ClusterAutoScalingMode":{ |
| 8362 | + "type":"string", |
| 8363 | + "enum":[ |
| 8364 | + "Enable", |
| 8365 | + "Disable" |
| 8366 | + ] |
| 8367 | + }, |
| 8368 | + "ClusterAutoScalingStatus":{ |
| 8369 | + "type":"string", |
| 8370 | + "enum":[ |
| 8371 | + "InService", |
| 8372 | + "Failed", |
| 8373 | + "Creating", |
| 8374 | + "Deleting" |
| 8375 | + ] |
| 8376 | + }, |
8316 | 8377 | "ClusterAvailabilityZone":{
|
8317 | 8378 | "type":"string",
|
8318 | 8379 | "pattern":"[a-z]{2}-[a-z]+-\\d[a-z]"
|
|
10483 | 10544 | "NodeProvisioningMode":{
|
10484 | 10545 | "shape":"ClusterNodeProvisioningMode",
|
10485 | 10546 | "documentation":"<p>The mode for provisioning nodes in the cluster. You can specify the following modes:</p> <ul> <li> <p> <b>Continuous</b>: Scaling behavior that enables 1) concurrent operation execution within instance groups, 2) continuous retry mechanisms for failed operations, 3) enhanced customer visibility into cluster events through detailed event streams, 4) partial provisioning capabilities. Your clusters and instance groups remain <code>InService</code> while scaling. This mode is only supported for EKS orchestrated clusters.</p> </li> </ul>"
|
| 10547 | + }, |
| 10548 | + "ClusterRole":{ |
| 10549 | + "shape":"RoleArn", |
| 10550 | + "documentation":"<p>The Amazon Resource Name (ARN) of the IAM role that HyperPod assumes to perform cluster autoscaling operations. This role must have permissions for <code>sagemaker:BatchAddClusterNodes</code> and <code>sagemaker:BatchDeleteClusterNodes</code>. This is only required when autoscaling is enabled and when HyperPod is performing autoscaling operations.</p>" |
| 10551 | + }, |
| 10552 | + "AutoScaling":{ |
| 10553 | + "shape":"ClusterAutoScalingConfig", |
| 10554 | + "documentation":"<p>The autoscaling configuration for the cluster. Enables automatic scaling of cluster nodes based on workload demand using a Karpenter-based system.</p>" |
10486 | 10555 | }
|
10487 | 10556 | }
|
10488 | 10557 | },
|
|
15551 | 15620 | "NodeProvisioningMode":{
|
15552 | 15621 | "shape":"ClusterNodeProvisioningMode",
|
15553 | 15622 | "documentation":"<p>The mode used for provisioning nodes in the cluster.</p>"
|
| 15623 | + }, |
| 15624 | + "ClusterRole":{ |
| 15625 | + "shape":"RoleArn", |
| 15626 | + "documentation":"<p>The Amazon Resource Name (ARN) of the IAM role that HyperPod uses for cluster autoscaling operations.</p>" |
| 15627 | + }, |
| 15628 | + "AutoScaling":{ |
| 15629 | + "shape":"ClusterAutoScalingConfigOutput", |
| 15630 | + "documentation":"<p>The current autoscaling configuration and status for the autoscaler.</p>" |
15554 | 15631 | }
|
15555 | 15632 | }
|
15556 | 15633 | },
|
|
43560 | 43637 | "InstanceGroupsToDelete":{
|
43561 | 43638 | "shape":"ClusterInstanceGroupsToDelete",
|
43562 | 43639 | "documentation":"<p>Specify the names of the instance groups to delete. Use a single <code>,</code> as the separator between multiple names.</p>"
|
| 43640 | + }, |
| 43641 | + "ClusterRole":{ |
| 43642 | + "shape":"RoleArn", |
| 43643 | + "documentation":"<p>The Amazon Resource Name (ARN) of the IAM role that HyperPod assumes for cluster autoscaling operations. Cannot be updated while autoscaling is enabled.</p>" |
| 43644 | + }, |
| 43645 | + "AutoScaling":{ |
| 43646 | + "shape":"ClusterAutoScalingConfig", |
| 43647 | + "documentation":"<p>Updates the autoscaling configuration for the cluster. Use to enable or disable automatic node scaling.</p>" |
43563 | 43648 | }
|
43564 | 43649 | }
|
43565 | 43650 | },
|
|
0 commit comments