|
3602 | 3602 | },
|
3603 | 3603 | "documentation":"<p>Lists a summary of the properties of an association. An association is an entity that links other lineage or experiment entities. An example would be an association between a training job and a model.</p>"
|
3604 | 3604 | },
|
| 3605 | + "AsyncInferenceClientConfig":{ |
| 3606 | + "type":"structure", |
| 3607 | + "members":{ |
| 3608 | + "MaxConcurrentInvocationsPerInstance":{ |
| 3609 | + "shape":"MaxConcurrentInvocationsPerInstance", |
| 3610 | + "documentation":"<p>The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.</p>" |
| 3611 | + } |
| 3612 | + }, |
| 3613 | + "documentation":"<p>Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.</p>" |
| 3614 | + }, |
| 3615 | + "AsyncInferenceConfig":{ |
| 3616 | + "type":"structure", |
| 3617 | + "required":["OutputConfig"], |
| 3618 | + "members":{ |
| 3619 | + "ClientConfig":{ |
| 3620 | + "shape":"AsyncInferenceClientConfig", |
| 3621 | + "documentation":"<p>Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.</p>" |
| 3622 | + }, |
| 3623 | + "OutputConfig":{ |
| 3624 | + "shape":"AsyncInferenceOutputConfig", |
| 3625 | + "documentation":"<p>Specifies the configuration for asynchronous inference invocation outputs.</p>" |
| 3626 | + } |
| 3627 | + }, |
| 3628 | + "documentation":"<p>Specifies configuration for how an endpoint performs asynchronous inference.</p>" |
| 3629 | + }, |
| 3630 | + "AsyncInferenceNotificationConfig":{ |
| 3631 | + "type":"structure", |
| 3632 | + "members":{ |
| 3633 | + "SuccessTopic":{ |
| 3634 | + "shape":"SnsTopicArn", |
| 3635 | + "documentation":"<p>Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.</p>" |
| 3636 | + }, |
| 3637 | + "ErrorTopic":{ |
| 3638 | + "shape":"SnsTopicArn", |
| 3639 | + "documentation":"<p>Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.</p>" |
| 3640 | + } |
| 3641 | + }, |
| 3642 | + "documentation":"<p>Specifies the configuration for notifications of inference results for asynchronous inference.</p>" |
| 3643 | + }, |
| 3644 | + "AsyncInferenceOutputConfig":{ |
| 3645 | + "type":"structure", |
| 3646 | + "required":["S3OutputPath"], |
| 3647 | + "members":{ |
| 3648 | + "KmsKeyId":{ |
| 3649 | + "shape":"KmsKeyId", |
| 3650 | + "documentation":"<p>The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.</p> <p/>" |
| 3651 | + }, |
| 3652 | + "S3OutputPath":{ |
| 3653 | + "shape":"DestinationS3Uri", |
| 3654 | + "documentation":"<p>The Amazon S3 location to upload inference responses to.</p>" |
| 3655 | + }, |
| 3656 | + "NotificationConfig":{ |
| 3657 | + "shape":"AsyncInferenceNotificationConfig", |
| 3658 | + "documentation":"<p>Specifies the configuration for notifications of inference results for asynchronous inference.</p>" |
| 3659 | + } |
| 3660 | + }, |
| 3661 | + "documentation":"<p>Specifies the configuration for asynchronous inference invocation outputs.</p>" |
| 3662 | + }, |
3605 | 3663 | "AthenaCatalog":{
|
3606 | 3664 | "type":"string",
|
3607 | 3665 | "documentation":"<p>The name of the data catalog used in Athena query execution.</p>",
|
|
4891 | 4949 | "ContainerDefinitionList":{
|
4892 | 4950 | "type":"list",
|
4893 | 4951 | "member":{"shape":"ContainerDefinition"},
|
4894 |
| - "max":5 |
| 4952 | + "max":15 |
4895 | 4953 | },
|
4896 | 4954 | "ContainerEntrypoint":{
|
4897 | 4955 | "type":"list",
|
|
5664 | 5722 | "KmsKeyId":{
|
5665 | 5723 | "shape":"KmsKeyId",
|
5666 | 5724 | "documentation":"<p>The Amazon Resource Name (ARN) of a Amazon Web Services Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.</p> <p>The KmsKeyId can be any of the following formats: </p> <ul> <li> <p>Key ID: <code>1234abcd-12ab-34cd-56ef-1234567890ab</code> </p> </li> <li> <p>Key ARN: <code>arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab</code> </p> </li> <li> <p>Alias name: <code>alias/ExampleAlias</code> </p> </li> <li> <p>Alias name ARN: <code>arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias</code> </p> </li> </ul> <p>The KMS key policy must grant permission to the IAM role that you specify in your <code>CreateEndpoint</code>, <code>UpdateEndpoint</code> requests. For more information, refer to the Amazon Web Services Key Management Service section<a href=\"https://docs.aws.amazon.com/kms/latest/developerguide/key-policies.html\"> Using Key Policies in Amazon Web Services KMS </a> </p> <note> <p>Certain Nitro-based instances include local storage, dependent on the instance type. Local storage volumes are encrypted using a hardware module on the instance. You can't request a <code>KmsKeyId</code> when using an instance type with local storage. If any of the models that you specify in the <code>ProductionVariants</code> parameter use nitro-based instances with local storage, do not specify a value for the <code>KmsKeyId</code> parameter. If you specify a value for <code>KmsKeyId</code> when using any nitro-based instances with local storage, the call to <code>CreateEndpointConfig</code> fails.</p> <p>For a list of instance types that support local instance storage, see <a href=\"https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html#instance-store-volumes\">Instance Store Volumes</a>.</p> <p>For more information about local instance storage encryption, see <a href=\"https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ssd-instance-store.html\">SSD Instance Store Volumes</a>.</p> </note>"
|
| 5725 | + }, |
| 5726 | + "AsyncInferenceConfig":{ |
| 5727 | + "shape":"AsyncInferenceConfig", |
| 5728 | + "documentation":"<p>Specifies configuration for how an endpoint performs asynchronous inference. This is a required field in order for your Endpoint to be invoked using <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_runtime_InvokeEndpoint.html\"> <code>InvokeEndpointAsync</code> </a>.</p>" |
5667 | 5729 | }
|
5668 | 5730 | }
|
5669 | 5731 | },
|
|
6445 | 6507 | "RootAccess":{
|
6446 | 6508 | "shape":"RootAccess",
|
6447 | 6509 | "documentation":"<p>Whether root access is enabled or disabled for users of the notebook instance. The default value is <code>Enabled</code>.</p> <note> <p>Lifecycle configurations need root access to be able to set up a notebook instance. Because of this, lifecycle configurations associated with a notebook instance always run with root access even if you disable root access for users.</p> </note>"
|
| 6510 | + }, |
| 6511 | + "PlatformIdentifier":{ |
| 6512 | + "shape":"PlatformIdentifier", |
| 6513 | + "documentation":"<p>The platform identifier of the notebook instance runtime environment.</p>" |
6448 | 6514 | }
|
6449 | 6515 | }
|
6450 | 6516 | },
|
|
8995 | 9061 | "CreationTime":{
|
8996 | 9062 | "shape":"Timestamp",
|
8997 | 9063 | "documentation":"<p>A timestamp that shows when the endpoint configuration was created.</p>"
|
| 9064 | + }, |
| 9065 | + "AsyncInferenceConfig":{ |
| 9066 | + "shape":"AsyncInferenceConfig", |
| 9067 | + "documentation":"<p>Returns the description of an endpoint configuration created using the <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html\"> <code>CreateEndpointConfig</code> </a> API.</p>" |
8998 | 9068 | }
|
8999 | 9069 | }
|
9000 | 9070 | },
|
|
9055 | 9125 | "LastDeploymentConfig":{
|
9056 | 9126 | "shape":"DeploymentConfig",
|
9057 | 9127 | "documentation":"<p>The most recent deployment configuration for the endpoint.</p>"
|
| 9128 | + }, |
| 9129 | + "AsyncInferenceConfig":{ |
| 9130 | + "shape":"AsyncInferenceConfig", |
| 9131 | + "documentation":"<p>Returns the description of an endpoint configuration created using the <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html\"> <code>CreateEndpointConfig</code> </a> API.</p>" |
9058 | 9132 | }
|
9059 | 9133 | }
|
9060 | 9134 | },
|
|
10148 | 10222 | "RootAccess":{
|
10149 | 10223 | "shape":"RootAccess",
|
10150 | 10224 | "documentation":"<p>Whether root access is enabled or disabled for users of the notebook instance.</p> <note> <p>Lifecycle configurations need root access to be able to set up a notebook instance. Because of this, lifecycle configurations associated with a notebook instance always run with root access even if you disable root access for users.</p> </note>"
|
| 10225 | + }, |
| 10226 | + "PlatformIdentifier":{ |
| 10227 | + "shape":"PlatformIdentifier", |
| 10228 | + "documentation":"<p>The platform identifier of the notebook instance runtime environment.</p>" |
10151 | 10229 | }
|
10152 | 10230 | }
|
10153 | 10231 | },
|
|
13468 | 13546 | },
|
13469 | 13547 | "documentation":"<p>Defines how to perform inference generation after a training job is run.</p>"
|
13470 | 13548 | },
|
| 13549 | + "InitialTaskCount":{ |
| 13550 | + "type":"integer", |
| 13551 | + "min":1 |
| 13552 | + }, |
13471 | 13553 | "InputConfig":{
|
13472 | 13554 | "type":"structure",
|
13473 | 13555 | "required":[
|
|
13534 | 13616 | "ml.m5.4xlarge",
|
13535 | 13617 | "ml.m5.12xlarge",
|
13536 | 13618 | "ml.m5.24xlarge",
|
| 13619 | + "ml.m5d.large", |
| 13620 | + "ml.m5d.xlarge", |
| 13621 | + "ml.m5d.2xlarge", |
| 13622 | + "ml.m5d.4xlarge", |
| 13623 | + "ml.m5d.8xlarge", |
| 13624 | + "ml.m5d.12xlarge", |
| 13625 | + "ml.m5d.16xlarge", |
| 13626 | + "ml.m5d.24xlarge", |
13537 | 13627 | "ml.c4.xlarge",
|
13538 | 13628 | "ml.c4.2xlarge",
|
13539 | 13629 | "ml.c4.4xlarge",
|
|
13553 | 13643 | "ml.p2.16xlarge",
|
13554 | 13644 | "ml.p3.2xlarge",
|
13555 | 13645 | "ml.p3.8xlarge",
|
13556 |
| - "ml.p3.16xlarge" |
| 13646 | + "ml.p3.16xlarge", |
| 13647 | + "ml.p3dn.24xlarge", |
| 13648 | + "ml.g4dn.xlarge", |
| 13649 | + "ml.g4dn.2xlarge", |
| 13650 | + "ml.g4dn.4xlarge", |
| 13651 | + "ml.g4dn.8xlarge", |
| 13652 | + "ml.g4dn.12xlarge", |
| 13653 | + "ml.g4dn.16xlarge", |
| 13654 | + "ml.r5.large", |
| 13655 | + "ml.r5.xlarge", |
| 13656 | + "ml.r5.2xlarge", |
| 13657 | + "ml.r5.4xlarge", |
| 13658 | + "ml.r5.8xlarge", |
| 13659 | + "ml.r5.12xlarge", |
| 13660 | + "ml.r5.16xlarge", |
| 13661 | + "ml.r5.24xlarge" |
13557 | 13662 | ]
|
13558 | 13663 | },
|
13559 | 13664 | "Integer":{"type":"integer"},
|
|
16830 | 16935 | "type":"integer",
|
16831 | 16936 | "min":1
|
16832 | 16937 | },
|
| 16938 | + "MaxConcurrentInvocationsPerInstance":{ |
| 16939 | + "type":"integer", |
| 16940 | + "max":1000, |
| 16941 | + "min":1 |
| 16942 | + }, |
16833 | 16943 | "MaxConcurrentTaskCount":{
|
16834 | 16944 | "type":"integer",
|
16835 | 16945 | "max":1000,
|
|
17368 | 17478 | "ModelPackageContainerDefinitionList":{
|
17369 | 17479 | "type":"list",
|
17370 | 17480 | "member":{"shape":"ModelPackageContainerDefinition"},
|
17371 |
| - "max":5, |
| 17481 | + "max":15, |
17372 | 17482 | "min":1
|
17373 | 17483 | },
|
17374 | 17484 | "ModelPackageGroup":{
|
@@ -18611,10 +18721,10 @@
|
18611 | 18721 | "members":{
|
18612 | 18722 | "NotificationTopicArn":{
|
18613 | 18723 | "shape":"NotificationTopicArn",
|
18614 |
| - "documentation":"<p>The ARN for the SNS topic to which notifications should be published.</p>" |
| 18724 | + "documentation":"<p>The ARN for the Amazon SNS topic to which notifications should be published.</p>" |
18615 | 18725 | }
|
18616 | 18726 | },
|
18617 |
| - "documentation":"<p>Configures SNS notifications of available or expiring work items for work teams.</p>" |
| 18727 | + "documentation":"<p>Configures Amazon SNS notifications of available or expiring work items for work teams.</p>" |
18618 | 18728 | },
|
18619 | 18729 | "NotificationTopicArn":{
|
18620 | 18730 | "type":"string",
|
|
19372 | 19482 | "max":100,
|
19373 | 19483 | "min":0
|
19374 | 19484 | },
|
| 19485 | + "PlatformIdentifier":{ |
| 19486 | + "type":"string", |
| 19487 | + "max":15, |
| 19488 | + "pattern":"^(notebook-al1-v1|notebook-al2-v1)$" |
| 19489 | + }, |
19375 | 19490 | "PolicyString":{
|
19376 | 19491 | "type":"string",
|
19377 | 19492 | "max":20480,
|
|
19880 | 19995 | "documentation":"<p>The name of the model that you want to host. This is the name that you specified when creating the model.</p>"
|
19881 | 19996 | },
|
19882 | 19997 | "InitialInstanceCount":{
|
19883 |
| - "shape":"TaskCount", |
| 19998 | + "shape":"InitialTaskCount", |
19884 | 19999 | "documentation":"<p>Number of instances to launch initially.</p>"
|
19885 | 20000 | },
|
19886 | 20001 | "InstanceType":{
|
|
21792 | 21907 | },
|
21793 | 21908 | "TaskCount":{
|
21794 | 21909 | "type":"integer",
|
21795 |
| - "min":1 |
| 21910 | + "min":0 |
21796 | 21911 | },
|
21797 | 21912 | "TaskDescription":{
|
21798 | 21913 | "type":"string",
|
|
0 commit comments