AWS sagemaker documentation change
Summary
Updated deployment setup instructions with cluster compatibility checks, GPU partitioning options, and priority settings
Security assessment
Focuses on resource management and deployment configuration without security-specific content
Diff
diff --git a/sagemaker/latest/dg/sagemaker-hyperpod-model-deployment-setup.md b/sagemaker/latest/dg/sagemaker-hyperpod-model-deployment-setup.md index 20f4e4426..e15d1ed0e 100644 --- a//sagemaker/latest/dg/sagemaker-hyperpod-model-deployment-setup.md +++ b//sagemaker/latest/dg/sagemaker-hyperpod-model-deployment-setup.md @@ -712 +712 @@ Access the helm chart from [https://github.com/aws/sagemaker-hyperpod-cli/tree/m - 4. Write the model input file. This creates a JSON input file containing sample data to test the deployed model's question-answering capabilities. + 4. Under **Deployment settings** , JumpStart will recommend an instance for deployment. You can modify these settings if necessary. @@ -714,2 +714 @@ Access the helm chart from [https://github.com/aws/sagemaker-hyperpod-cli/tree/m - %%writefile demo-input.json - {"question" :"what is the name of the planet?","context" : "earth"} + 1. If you modify **Instance type** , ensure it's compatible with the chosen **HyperPod cluster**. If there aren't any compatible instances, you'll need to select a new **HyperPod cluster** or contact your admin to add compatible instances to the cluster. @@ -717 +716 @@ Access the helm chart from [https://github.com/aws/sagemaker-hyperpod-cli/tree/m - 5. Invoke the SageMaker endpoint to perform load testing to validate the inference endpoint's performance and reliability. + 2. If your selected instance type supports GPU partitioning and your cluster is configured with MIG, you can select a specific **GPU partition** from the available MIG profiles. This allows you to optimize GPU utilization by allocating only the required GPU resources for your model. For more information, see [Using GPU partitions in Amazon SageMaker HyperPod](./sagemaker-hyperpod-eks-gpu-partitioning.html). @@ -719 +718 @@ Access the helm chart from [https://github.com/aws/sagemaker-hyperpod-cli/tree/m - %%bash + 3. To prioritize the model deployment, install the task governance addon, create compute allocations, and set up task rankings for the cluster policy. Once this is done, you should see an option to select a priority for the model deployment which can be used for preemption of other deployments and tasks on the cluster. @@ -721,17 +720 @@ Access the helm chart from [https://github.com/aws/sagemaker-hyperpod-cli/tree/m - #!/bin/bash - - for i in {1..1000} - do - echo "Invocation #$i" - aws sagemaker-runtime invoke-endpoint \ - --endpoint-name testing-deployment-jumpstart-9 \ - --region {REGION} \ - --body fileb://demo-input.json \ - --content-type application/list-text \ - --accept application/json \ - "demoout_${i}.json" - - # Add a small delay to prevent throttling (optional) - #sleep 0.5 - rm -f "demoout_${i}.json" - done + 4. Enter the namespace to which your admin has provided you access. You may have to directly reach out to your admin to get the exact namespace. Once a valid namespace is provided, the **Deploy** button should be enabled to deploy the model.