Merge latest changes from main to 'Documentation' branch

.github/workflows/codebuild-ci.yml

@@ -2,8 +2,7 @@ name: PR Checks
 on:
   pull_request_target:
       branches:
-          - "master*"
-          - "main*"
+          - "*"
 
 concurrency:
     group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref }}

.github/workflows/security-monitoring.yml

@@ -73,7 +73,7 @@ jobs:
         uses: aws-actions/configure-aws-credentials@12e3392609eaaceb7ae6191b3f54bbcb85b5002b
         with:
           role-to-assume: ${{ secrets.MONITORING_ROLE_ARN }}
-          aws-region: us-west-2
+          aws-region: us-east-2
       - name: Put Dependabot Alert Metric Data
         run: |
           if [ "${{ needs.check-dependabot-alerts.outputs.dependabot_alert_status }}" == "1" ]; then

.gitignore

@@ -16,11 +16,13 @@ __pycache__/
 /.mypy_cache
 
 /doc/_apidoc/
+doc/_build/
 /build
 
 /sagemaker-hyperpod/build
 /sagemaker-hyperpod/.coverage
 /sagemaker-hyperpod/.coverage.*
+/hyperpod-cluster-stack-template/build
 
 # Ignore all contents of result and results directories
 /result/

.readthedocs.yaml

@@ -0,0 +1,20 @@
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+
+python:
+  install:
+    - method: pip
+      path: .
+    - requirements: doc/requirements.txt
+
+sphinx:
+  configuration: doc/conf.py
+  fail_on_warning: false
+
+formats:
+  - pdf
+  - epub

CHANGELOG.md

@@ -1,23 +1,58 @@
 # Changelog
 
-## v2.0.0 (2024-12-04)
+## v3.2.1 (2025-08-27)
 
 ### Features
 
-- feature: The HyperPod CLI now support ([Hyperpod recipes](https://github.com/aws/sagemaker-hyperpod-recipes.git)). The HyperPod recipes enable customers to get started training and fine-tuning popular publicly-available foundation models like Llama 3.1 405B in minutes. Learn more ([here](https://github.com/aws/sagemaker-hyperpod-recipes.git)).
+ * Cluster management 
+   * Bug Fixes with cluster creation
+   * Enable cluster template to be installed with hyperpod CLI .
 
-## v1.0.0 (2024-09-09)
+## v3.2.0 (2025-08-25)
 
 ### Features
 
-- feature: Add support for SageMaker HyperPod CLI
+ * Cluster management 
+   * Creation of cluster stack 
+   * Describing and listing a cluster stack 
+   * Updating a cluster 
+ * Init Experience 
+   * Init, Validate, Create with local configurations
+
+
+## v3.1.0 (2025-08-13)
+
+### Features
+ * Task Governance feature for training jobs.
 
 
-## v1.0.0] ([2025]-[07]-[10])
+## v3.0.2 (2025-07-31)
+
+### Features
+
+ * Update volume flag to support hostPath and PVC
+ * Add an option to disable the deployment of KubeFlow TrainingOperator
+ * Enable telemetry for CLI
+
+## v3.0.0 (2025-07-10)
 
 ### Features
 
  * Training Job - Create, List , Get 
  * Inference Jumpstart - Create , List, Get, Invoke
  * Inference Custom - Create , List, Get, Invoke
- * Observability changes
+ * Observability changes
+
+## v2.0.0 (2024-12-04)
+
+### Features
+
+- feature: The HyperPod CLI now support ([Hyperpod recipes](https://github.com/aws/sagemaker-hyperpod-recipes.git)). The HyperPod recipes enable customers to get started training and fine-tuning popular publicly-available foundation models like Llama 3.1 405B in minutes. Learn more ([here](https://github.com/aws/sagemaker-hyperpod-recipes.git)).
+
+## v1.0.0 (2024-09-09)
+
+### Features
+
+- feature: Add support for SageMaker HyperPod CLI
+
+

README.md

@@ -54,24 +54,13 @@ SageMaker HyperPod CLI currently supports start training job with:
 
 1. Make sure that your local python version is 3.8, 3.9, 3.10 or 3.11.
 
-1. Install ```helm```.
-
-    The SageMaker Hyperpod CLI uses Helm to start training jobs. See also the [Helm installation guide](https://helm.sh/docs/intro/install/).
-
-    ```
-    curl -fsSL -o get_helm.sh https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3
-    chmod 700 get_helm.sh
-    ./get_helm.sh
-    rm -f ./get_helm.sh  
-    ```
-
-1. Clone and install the sagemaker-hyperpod-cli package.
+2. Install the sagemaker-hyperpod-cli package.
 
     ```
     pip install sagemaker-hyperpod
     ```
 
-1. Verify if the installation succeeded by running the following command.
+3. Verify if the installation succeeded by running the following command.
 
     ```
     hyp --help
@@ -158,8 +147,8 @@ hyp create hyp-pytorch-job \
     --version 1.0 \
     --job-name test-pytorch-job \
     --image pytorch/pytorch:latest \
-    --command '["python", "train.py"]' \
-    --args '["--epochs", "10", "--batch-size", "32"]' \
+    --command '[python, train.py]' \
+    --args '[--epochs=10, --batch-size=32]' \
     --environment '{"PYTORCH_CUDA_ALLOC_CONF": "max_split_size_mb:32"}' \
     --pull-policy "IfNotPresent" \
     --instance-type ml.p4d.24xlarge \
@@ -170,9 +159,15 @@ hyp create hyp-pytorch-job \
     --queue-name "training-queue" \
     --priority "high" \
     --max-retry 3 \
-    --volumes '["data-vol", "model-vol", "checkpoint-vol"]' \
-    --persistent-volume-claims '["shared-data-pvc", "model-registry-pvc"]' \
-    --output-s3-uri s3://my-bucket/model-artifacts
+    --accelerators 8 \
+    --vcpu 96.0 \
+    --memory 1152.0 \
+    --accelerators-limit 8 \
+    --vcpu-limit 96.0 \
+    --memory-limit 1152.0 \
+    --preferred-topology "topology.kubernetes.io/zone=us-west-2a" \
+    --volume name=model-data,type=hostPath,mount_path=/data,path=/data \
+    --volume name=training-output,type=pvc,mount_path=/data2,claim_name=my-pvc,read_only=false
 ```
 
 Key required parameters explained:
@@ -181,8 +176,6 @@ Key required parameters explained:
 
     --image: Docker image containing your training environment
 
-This command starts a training job named test-pytorch-job. The --output-s3-uri specifies where the trained model artifacts will be stored, for example, s3://my-bucket/model-artifacts. Note this location, as you’ll need it for deploying the custom model.
-
 ### Inference 
 
 #### Creating a JumpstartModel Endpoint
@@ -195,7 +188,6 @@ hyp create hyp-jumpstart-endpoint \
     --model-id jumpstart-model-id\
     --instance-type ml.g5.8xlarge \
     --endpoint-name endpoint-jumpstart \
-    --tls-output-s3-uri s3://sample-bucket
 ```
 
 
@@ -211,7 +203,7 @@ hyp invoke hyp-jumpstart-endpoint \
 
 ```
 hyp list hyp-jumpstart-endpoint
-hyp get hyp-jumpstart-endpoint --name endpoint-jumpstart
+hyp describe hyp-jumpstart-endpoint --name endpoint-jumpstart
 ```
 
 #### Creating a Custom Inference Endpoint 
@@ -222,7 +214,8 @@ hyp create hyp-custom-endpoint \
     --endpoint-name my-custom-endpoint \
     --model-name my-pytorch-model \
     --model-source-type s3 \
-    --model-location my-pytorch-training/model.tar.gz \
+    --model-location my-pytorch-training \
+    --model-volume-mount-name test-volume \
     --s3-bucket-name your-bucket \
     --s3-region us-east-1 \
     --instance-type ml.g5.8xlarge \
@@ -257,9 +250,10 @@ Along with the CLI, we also have SDKs available that can perform the training an
 
 ```
 
-from sagemaker.hyperpod import HyperPodPytorchJob
-from sagemaker.hyperpod.job 
-import ReplicaSpec, Template, Spec, Container, Resources, RunPolicy, Metadata
+from sagemaker.hyperpod.training import HyperPodPytorchJob
+from sagemaker.hyperpod.training
+import ReplicaSpec, Template, Spec, Containers, Resources, RunPolicy
+from sagemaker.hyperpod.common.config import Metadata
 
 # Define job specifications
 nproc_per_node = "1"  # Number of processes per node
@@ -274,7 +268,7 @@ replica_specs =
             (
                 containers =
                 [
-                    Container
+                    Containers
                     (
                         # Container name
                         name="container-name",  
@@ -315,8 +309,6 @@ pytorch_job = HyperPodPytorchJob
     replica_specs = replica_specs,     
     # Run policy
     run_policy = run_policy,           
-    # S3 location for artifacts
-    output_s3_uri="s3://my-bucket/model-artifacts"  
 )
 # Launch the job
 pytorch_job.create()  
@@ -336,24 +328,18 @@ Pre-trained Jumpstart models can be gotten from https://sagemaker.readthedocs.io
 from sagemaker.hyperpod.inference.config.hp_jumpstart_endpoint_config import Model, Server, SageMakerEndpoint, TlsConfig
 from sagemaker.hyperpod.inference.hp_jumpstart_endpoint import HPJumpStartEndpoint
 
-model = Model(
-    model_id="deepseek-llm-r1-distill-qwen-1-5b",
-    model_version="2.0.4"
+model=Model(
+    model_id='deepseek-llm-r1-distill-qwen-1-5b'
 )
-
-server = Server(
-    instance_type="ml.g5.8xlarge"
+server=Server(
+    instance_type='ml.g5.8xlarge',
 )
+endpoint_name=SageMakerEndpoint(name='<my-endpoint-name>')
 
-endpoint_name = SageMakerEndpoint(name="endpoint-jumpstart")
-
-tls_config = TlsConfig(tls_certificate_output_s3_uri="s3://sample-bucket")
-
-js_endpoint = HPJumpStartEndpoint(
+js_endpoint=HPJumpStartEndpoint(
     model=model,
     server=server,
-    sage_maker_endpoint=endpoint_name,
-    tls_config=tls_config
+    sage_maker_endpoint=endpoint_name
 )
 
 js_endpoint.create()
@@ -369,51 +355,51 @@ print(response)
 ```
 
 
-#### Creating a Custom Inference Endpoint 
+#### Creating a Custom Inference Endpoint (with S3)
 
 ```
-from sagemaker.hyperpod.inference.config.hp_custom_endpoint_config import Model, Server, SageMakerEndpoint, TlsConfig, EnvironmentVariables
-from sagemaker.hyperpod.inference.hp_custom_endpoint import HPCustomEndpoint
+from sagemaker.hyperpod.inference.config.hp_endpoint_config import CloudWatchTrigger, Dimensions, AutoScalingSpec, Metrics, S3Storage, ModelSourceConfig, TlsConfig, EnvironmentVariables, ModelInvocationPort, ModelVolumeMount, Resources, Worker
+from sagemaker.hyperpod.inference.hp_endpoint import HPEndpoint
 
-model = Model(
-    model_source_type="s3",
-    model_location="test-pytorch-job/model.tar.gz",
-    s3_bucket_name="my-bucket",
-    s3_region="us-east-2",
-    prefetch_enabled=True
+model_source_config = ModelSourceConfig(
+    model_source_type='s3',
+    model_location="<my-model-folder-in-s3>",
+    s3_storage=S3Storage(
+        bucket_name='<my-model-artifacts-bucket>',
+        region='us-east-2',
+    ),
 )
 
-server = Server(
-    instance_type="ml.g5.8xlarge",
-    image_uri="763104351884.dkr.ecr.us-east-2.amazonaws.com/huggingface-pytorch-tgi-inference:2.4.0-tgi2.3.1-gpu-py311-cu124-ubuntu22.04-v2.0",
-    container_port=8080,
-    model_volume_mount_name="model-weights"
-)
+environment_variables = [
+    EnvironmentVariables(name="HF_MODEL_ID", value="/opt/ml/model"),
+    EnvironmentVariables(name="SAGEMAKER_PROGRAM", value="inference.py"),
+    EnvironmentVariables(name="SAGEMAKER_SUBMIT_DIRECTORY", value="/opt/ml/model/code"),
+    EnvironmentVariables(name="MODEL_CACHE_ROOT", value="/opt/ml/model"),
+    EnvironmentVariables(name="SAGEMAKER_ENV", value="1"),
+]
 
-resources = {
-    "requests": {"cpu": "30000m", "nvidia.com/gpu": 1, "memory": "100Gi"},
-    "limits": {"nvidia.com/gpu": 1}
-}
-
-env = EnvironmentVariables(
-    HF_MODEL_ID="/opt/ml/model",
-    SAGEMAKER_PROGRAM="inference.py",
-    SAGEMAKER_SUBMIT_DIRECTORY="/opt/ml/model/code",
-    MODEL_CACHE_ROOT="/opt/ml/model",
-    SAGEMAKER_ENV="1"
+worker = Worker(
+    image='763104351884.dkr.ecr.us-east-2.amazonaws.com/huggingface-pytorch-tgi-inference:2.4.0-tgi2.3.1-gpu-py311-cu124-ubuntu22.04-v2.0',
+    model_volume_mount=ModelVolumeMount(
+        name='model-weights',
+    ),
+    model_invocation_port=ModelInvocationPort(container_port=8080),
+    resources=Resources(
+            requests={"cpu": "30000m", "nvidia.com/gpu": 1, "memory": "100Gi"},
+            limits={"nvidia.com/gpu": 1}
+    ),
+    environment_variables=environment_variables,
 )
 
-endpoint_name = SageMakerEndpoint(name="endpoint-custom-pytorch")
+tls_config=TlsConfig(tls_certificate_output_s3_uri='s3://<my-tls-bucket-name>')
 
-tls_config = TlsConfig(tls_certificate_output_s3_uri="s3://sample-bucket")
-
-custom_endpoint = HPCustomEndpoint(
-    model=model,
-    server=server,
-    resources=resources,
-    environment=env,
-    sage_maker_endpoint=endpoint_name,
+custom_endpoint = HPEndpoint(
+    endpoint_name='<my-endpoint-name>',
+    instance_type='ml.g5.8xlarge',
+    model_name='deepseek15b-test-model-name',  
     tls_config=tls_config,
+    model_source_config=model_source_config,
+    worker=worker,
 )
 
 custom_endpoint.create()
@@ -430,19 +416,17 @@ print(response)
 #### Managing an Endpoint 
 
 ```
-endpoint_iterator = HPJumpStartEndpoint.list()
-for endpoint in endpoint_iterator:
-    print(endpoint.name, endpoint.status)
+endpoint_list = HPEndpoint.list()
+print(endpoint_list[0])
 
-logs = js_endpoint.get_logs()
-print(logs)
+print(custom_endpoint.get_operator_logs(since_hours=0.5))
 
 ```
 
 #### Deleting an Endpoint 
 
 ```
-js_endpoint.delete()
+custom_endpoint.delete()
 
 ```