Skip to content

Commit c84177f

Browse files
author
awstools
committed
feat(client-sagemaker): Sagemaker Neo now supports compilation for inferentia2 (ML_INF2) and Trainium1 (ML_TRN1) as available targets. With these devices, you can run your workloads at highest performance with lowest cost. inferentia2 (ML_INF2) is available in CMH and Trainium1 (ML_TRN1) is available in IAD currently
1 parent be0249f commit c84177f

15 files changed

+357
-321
lines changed

clients/client-sagemaker/src/commands/AddTagsCommand.ts

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,8 @@ export interface AddTagsCommandOutput extends AddTagsOutput, __MetadataBearer {}
5959
* this API. To make sure that the tags associated with a Domain or User Profile are
6060
* also added to all Apps that the Domain or User Profile launches, add the tags when
6161
* you first create the Domain or User Profile by specifying them in the
62-
* <code>Tags</code> parameter of <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateDomain.html">CreateDomain</a> or <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateUserProfile.html">CreateUserProfile</a>.</p>
62+
* <code>Tags</code> parameter of <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateDomain.html">CreateDomain</a>
63+
* or <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateUserProfile.html">CreateUserProfile</a>.</p>
6364
* </note>
6465
* @example
6566
* Use a bare-bones client and the command you need to make an API call.

clients/client-sagemaker/src/commands/CreateCompilationJobCommand.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -86,7 +86,7 @@ export interface CreateCompilationJobCommandOutput extends CreateCompilationJobR
8686
* },
8787
* OutputConfig: { // OutputConfig
8888
* S3OutputLocation: "STRING_VALUE", // required
89-
* TargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
89+
* TargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_inf2" || "ml_trn1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
9090
* TargetPlatform: { // TargetPlatform
9191
* Os: "ANDROID" || "LINUX", // required
9292
* Arch: "X86_64" || "X86" || "ARM64" || "ARM_EABI" || "ARM_EABIHF", // required

clients/client-sagemaker/src/commands/CreateEndpointCommand.ts

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -54,22 +54,22 @@ export interface CreateEndpointCommandOutput extends CreateEndpointOutput, __Met
5454
* <p>When it receives the request, SageMaker creates the endpoint, launches the resources (ML
5555
* compute instances), and deploys the model(s) on them. </p>
5656
* <note>
57-
* <p>When you call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a>, a load call is made to DynamoDB to
58-
* verify that your endpoint configuration exists. When you read data from a DynamoDB
59-
* table supporting <a href="https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/HowItWorks.ReadConsistency.html">
57+
* <p>When you call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a>, a load call is made to DynamoDB to verify that your
58+
* endpoint configuration exists. When you read data from a DynamoDB table supporting
59+
* <a href="https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/HowItWorks.ReadConsistency.html">
6060
* <code>Eventually Consistent Reads</code>
6161
* </a>, the response might not
6262
* reflect the results of a recently completed write operation. The response might
6363
* include some stale data. If the dependent entities are not yet in DynamoDB, this
6464
* causes a validation error. If you repeat your read request after a short time, the
6565
* response should return the latest data. So retry logic is recommended to handle
66-
* these possible issues. We also recommend that customers call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpointConfig.html">DescribeEndpointConfig</a> before calling <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> to minimize the potential impact of a DynamoDB eventually consistent read.</p>
66+
* these possible issues. We also recommend that customers call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpointConfig.html">DescribeEndpointConfig</a> before calling <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> to minimize the potential impact of a DynamoDB
67+
* eventually consistent read.</p>
6768
* </note>
6869
* <p>When SageMaker receives the request, it sets the endpoint status to
6970
* <code>Creating</code>. After it creates the endpoint, it sets the status to
7071
* <code>InService</code>. SageMaker can then process incoming requests for inferences. To
71-
* check the status of an endpoint, use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpoint.html">DescribeEndpoint</a>
72-
* API.</p>
72+
* check the status of an endpoint, use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpoint.html">DescribeEndpoint</a> API.</p>
7373
* <p>If any of the models hosted at this endpoint get model data from an Amazon S3 location,
7474
* SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the
7575
* S3 path you provided. Amazon Web Services STS is activated in your Amazon Web Services
@@ -82,8 +82,8 @@ export interface CreateEndpointCommandOutput extends CreateEndpointOutput, __Met
8282
* <note>
8383
* <p> To add the IAM role policies for using this API operation, go to the <a href="https://console.aws.amazon.com/iam/">IAM console</a>, and choose
8484
* Roles in the left navigation pane. Search the IAM role that you want to grant
85-
* access to use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html">CreateEndpointConfig</a> API operations, add the following policies to
86-
* the role. </p>
85+
* access to use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html">CreateEndpointConfig</a> API operations, add the following policies to the
86+
* role. </p>
8787
* <ul>
8888
* <li>
8989
* <p>Option 1: For a full SageMaker access, search and attach the

clients/client-sagemaker/src/commands/CreateEndpointConfigCommand.ts

Lines changed: 7 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -39,7 +39,8 @@ export interface CreateEndpointConfigCommandOutput extends CreateEndpointConfigO
3939
* <p>Creates an endpoint configuration that SageMaker hosting services uses to deploy models. In
4040
* the configuration, you identify one or more models, created using the
4141
* <code>CreateModel</code> API, to deploy and the resources that you want SageMaker to
42-
* provision. Then you call the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> API.</p>
42+
* provision. Then you call the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a>
43+
* API.</p>
4344
* <note>
4445
* <p> Use this API if you want to use SageMaker hosting services to deploy models into
4546
* production. </p>
@@ -54,16 +55,17 @@ export interface CreateEndpointConfigCommandOutput extends CreateEndpointConfigO
5455
* for model B. SageMaker distributes two-thirds of the traffic to Model A, and one-third to
5556
* model B. </p>
5657
* <note>
57-
* <p>When you call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a>, a load call is made to DynamoDB to
58-
* verify that your endpoint configuration exists. When you read data from a DynamoDB
59-
* table supporting <a href="https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/HowItWorks.ReadConsistency.html">
58+
* <p>When you call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a>, a load call is made to DynamoDB to verify that your
59+
* endpoint configuration exists. When you read data from a DynamoDB table supporting
60+
* <a href="https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/HowItWorks.ReadConsistency.html">
6061
* <code>Eventually Consistent Reads</code>
6162
* </a>, the response might not
6263
* reflect the results of a recently completed write operation. The response might
6364
* include some stale data. If the dependent entities are not yet in DynamoDB, this
6465
* causes a validation error. If you repeat your read request after a short time, the
6566
* response should return the latest data. So retry logic is recommended to handle
66-
* these possible issues. We also recommend that customers call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpointConfig.html">DescribeEndpointConfig</a> before calling <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> to minimize the potential impact of a DynamoDB eventually consistent read.</p>
67+
* these possible issues. We also recommend that customers call <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpointConfig.html">DescribeEndpointConfig</a> before calling <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html">CreateEndpoint</a> to minimize the potential impact of a DynamoDB
68+
* eventually consistent read.</p>
6769
* </note>
6870
* @example
6971
* Use a bare-bones client and the command you need to make an API call.

clients/client-sagemaker/src/commands/CreatePresignedNotebookInstanceUrlCommand.ts

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -55,9 +55,8 @@ export interface CreatePresignedNotebookInstanceUrlCommandOutput
5555
* <code>aws:SourceIP</code> condition context key to specify the list of IP addresses
5656
* that you want to have access to the notebook instance. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/security_iam_id-based-policy-examples.html#nbi-ip-filter">Limit Access to a Notebook Instance by IP Address</a>.</p>
5757
* <note>
58-
* <p>The URL that you get from a call to <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreatePresignedNotebookInstanceUrl.html">CreatePresignedNotebookInstanceUrl</a> is valid only for 5 minutes. If
59-
* you try to use the URL after the 5-minute limit expires, you are directed to the
60-
* Amazon Web Services console sign-in page.</p>
58+
* <p>The URL that you get from a call to <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreatePresignedNotebookInstanceUrl.html">CreatePresignedNotebookInstanceUrl</a> is valid only for 5 minutes. If you
59+
* try to use the URL after the 5-minute limit expires, you are directed to the Amazon Web Services console sign-in page.</p>
6160
* </note>
6261
* @example
6362
* Use a bare-bones client and the command you need to make an API call.

clients/client-sagemaker/src/commands/DescribeCompilationJobCommand.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -80,7 +80,7 @@ export interface DescribeCompilationJobCommandOutput extends DescribeCompilation
8080
* // },
8181
* // OutputConfig: { // OutputConfig
8282
* // S3OutputLocation: "STRING_VALUE", // required
83-
* // TargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
83+
* // TargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_inf2" || "ml_trn1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
8484
* // TargetPlatform: { // TargetPlatform
8585
* // Os: "ANDROID" || "LINUX", // required
8686
* // Arch: "X86_64" || "X86" || "ARM64" || "ARM_EABI" || "ARM_EABIHF", // required

clients/client-sagemaker/src/commands/ListCompilationJobsCommand.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@ export interface ListCompilationJobsCommandOutput extends ListCompilationJobsRes
6767
* // CreationTime: new Date("TIMESTAMP"), // required
6868
* // CompilationStartTime: new Date("TIMESTAMP"),
6969
* // CompilationEndTime: new Date("TIMESTAMP"),
70-
* // CompilationTargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
70+
* // CompilationTargetDevice: "lambda" || "ml_m4" || "ml_m5" || "ml_c4" || "ml_c5" || "ml_p2" || "ml_p3" || "ml_g4dn" || "ml_inf1" || "ml_inf2" || "ml_trn1" || "ml_eia2" || "jetson_tx1" || "jetson_tx2" || "jetson_nano" || "jetson_xavier" || "rasp3b" || "imx8qm" || "deeplens" || "rk3399" || "rk3288" || "aisage" || "sbe_c" || "qcs605" || "qcs603" || "sitara_am57x" || "amba_cv2" || "amba_cv22" || "amba_cv25" || "x86_win32" || "x86_win64" || "coreml" || "jacinto_tda4vm" || "imx8mplus",
7171
* // CompilationTargetPlatformOs: "ANDROID" || "LINUX",
7272
* // CompilationTargetPlatformArch: "X86_64" || "X86" || "ARM64" || "ARM_EABI" || "ARM_EABIHF",
7373
* // CompilationTargetPlatformAccelerator: "INTEL_GRAPHICS" || "MALI" || "NVIDIA" || "NNA",

clients/client-sagemaker/src/commands/ListTrainingJobsForHyperParameterTuningJobCommand.ts

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -45,8 +45,8 @@ export interface ListTrainingJobsForHyperParameterTuningJobCommandOutput
4545

4646
/**
4747
* @public
48-
* <p>Gets a list of <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_TrainingJobSummary.html">TrainingJobSummary</a> objects that describe the training
49-
* jobs that a hyperparameter tuning job launched.</p>
48+
* <p>Gets a list of <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_TrainingJobSummary.html">TrainingJobSummary</a> objects that describe the training jobs that a
49+
* hyperparameter tuning job launched.</p>
5050
* @example
5151
* Use a bare-bones client and the command you need to make an API call.
5252
* ```javascript

clients/client-sagemaker/src/commands/UpdateEndpointCommand.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,7 @@ export interface UpdateEndpointCommandOutput extends UpdateEndpointOutput, __Met
4141
* using the previous <code>EndpointConfig</code> (there is no availability loss). </p>
4242
* <p>When SageMaker receives the request, it sets the endpoint status to
4343
* <code>Updating</code>. After updating the endpoint, it sets the status to
44-
* <code>InService</code>. To check the status of an endpoint, use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpoint.html">DescribeEndpoint</a> API.
44+
* <code>InService</code>. To check the status of an endpoint, use the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpoint.html">DescribeEndpoint</a> API.
4545
*
4646
* </p>
4747
* <note>

0 commit comments

Comments
 (0)