Menyiapkan HyperPod cluster Anda untuk penerapan model

Konfigurasikan kubectl untuk terhubung ke HyperPod cluster yang baru dibuat yang diatur oleh klaster Amazon EKS. Tentukan nama Region dan HyperPod cluster.

export HYPERPOD_CLUSTER_NAME=<hyperpod-cluster-name>
export REGION=<region>

# S3 bucket where tls certificates will be uploaded
BUCKET_NAME="<Enter name of your s3 bucket>" # This should be bucket name, not URI

export EKS_CLUSTER_NAME=$(aws --region $REGION sagemaker describe-cluster --cluster-name $HYPERPOD_CLUSTER_NAME \
  --query 'Orchestrator.Eks.ClusterArn' --output text | \
  cut -d'/' -f2)
aws eks update-kubeconfig --name $EKS_CLUSTER_NAME --region $REGION

Tetapkan variabel env default.

LB_CONTROLLER_POLICY_NAME="AWSLoadBalancerControllerIAMPolicy-$HYPERPOD_CLUSTER_NAME"
LB_CONTROLLER_ROLE_NAME="aws-load-balancer-controller-$HYPERPOD_CLUSTER_NAME"
S3_MOUNT_ACCESS_POLICY_NAME="S3MountpointAccessPolicy-$HYPERPOD_CLUSTER_NAME"
S3_CSI_ROLE_NAME="SM_HP_S3_CSI_ROLE-$HYPERPOD_CLUSTER_NAME"
KEDA_OPERATOR_POLICY_NAME="KedaOperatorPolicy-$HYPERPOD_CLUSTER_NAME"
KEDA_OPERATOR_ROLE_NAME="keda-operator-role-$HYPERPOD_CLUSTER_NAME"
PRESIGNED_URL_ACCESS_POLICY_NAME="PresignedUrlAccessPolicy-$HYPERPOD_CLUSTER_NAME"
HYPERPOD_INFERENCE_ACCESS_POLICY_NAME="HyperpodInferenceAccessPolicy-$HYPERPOD_CLUSTER_NAME"
HYPERPOD_INFERENCE_ROLE_NAME="HyperpodInferenceRole-$HYPERPOD_CLUSTER_NAME"
HYPERPOD_INFERENCE_SA_NAME="hyperpod-inference-service-account"
HYPERPOD_INFERENCE_SA_NAMESPACE="kube-system"
JUMPSTART_GATED_ROLE_NAME="JumpstartGatedRole-$HYPERPOD_CLUSTER_NAME"
FSX_CSI_ROLE_NAME="AmazonEKSFSxLustreCSIDriverFullAccess-$HYPERPOD_CLUSTER_NAME"

Ekstrak nama klaster Amazon EKS dari ARN cluster, perbarui kubeconfig lokal, dan verifikasi konektivitas dengan mencantumkan semua pod di seluruh namespace.

kubectl get pods --all-namespaces

(Opsional) Instal plugin perangkat NVIDIA untuk mengaktifkan dukungan GPU di cluster.

#Install nvidia device plugin
kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.5/nvidia-device-plugin.yml
# Verify that GPUs are visible to k8s
kubectl get nodes -o=custom-columns=NAME:.metadata.name,GPU:.status.allocatable.nvidia.com/gpu

Kumpulkan pengidentifikasi AWS sumber daya penting dan ARNs diperlukan untuk mengonfigurasi integrasi layanan antara komponen EKS, SageMaker, dan IAM.

%%bash -x

export ACCOUNT_ID=$(aws --region $REGION sts get-caller-identity --query 'Account' --output text)
export OIDC_ID=$(aws --region $REGION eks describe-cluster --name $EKS_CLUSTER_NAME --query "cluster.identity.oidc.issuer" --output text | cut -d '/' -f 5)
export EKS_CLUSTER_ROLE=$(aws eks --region $REGION describe-cluster --name $EKS_CLUSTER_NAME --query 'cluster.roleArn' --output text)

Kaitkan OIDCidentity penyedia IAM dengan kluster EKS Anda.

eksctl utils associate-iam-oidc-provider --region=$REGION --cluster=$EKS_CLUSTER_NAME --approve

Buat dokumen JSON kebijakan kepercayaan dan kebijakan izin yang diperlukan untuk peran IAM operator HyperPod inferensi. Kebijakan ini memungkinkan komunikasi lintas layanan yang aman antara EKS, SageMaker, dan AWS layanan lainnya.

bash
# Create trust policy JSON
cat << EOF > trust-policy.json
{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Principal": {
                "Service": [
                    "sagemaker.amazonaws.com"
                ]
            },
            "Action": "sts:AssumeRole"
        },
        {
            "Effect": "Allow",
            "Principal": {
                "Federated": "arn:aws:iam::${ACCOUNT_ID}:oidc-provider/oidc.eks.${REGION}.amazonaws.com/id/${OIDC_ID}"
            },
            "Action": "sts:AssumeRoleWithWebIdentity",
            "Condition": {
                "StringLike": {
                    "oidc.eks.${REGION}.amazonaws.com/id/${OIDC_ID}:aud": "sts.amazonaws.com",
                    "oidc.eks.${REGION}.amazonaws.com/id/${OIDC_ID}:sub": "system:serviceaccount:*:*"
                }
            }
        }
    ]
}
EOF

# Create permission policy JSON
cat << EOF > permission-policy.json
{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": [
                "s3:ListBucket",
                "s3:PutObject",
                "s3:GetObject",
                "s3:DeleteObject"
            ],
            "Resource": [
                "arn:aws:s3:::$BUCKET_NAME"
                "arn:aws:s3:::$BUCKET_NAME/*"
            ]
        },
        {
            "Effect": "Allow",
            "Action": [
                "ecr:GetAuthorizationToken"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "ecr:BatchCheckLayerAvailability",
                "ecr:GetDownloadUrlForLayer",
                "ecr:GetRepositoryPolicy",
                "ecr:DescribeRepositories",
                "ecr:ListImages",
                "ecr:DescribeImages",
                "ecr:BatchGetImage",
                "ecr:GetLifecyclePolicy",
                "ecr:GetLifecyclePolicyPreview",
                "ecr:ListTagsForResource",
                "ecr:DescribeImageScanFindings"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "ec2:AssignPrivateIpAddresses",
                "ec2:AttachNetworkInterface",
                "ec2:CreateNetworkInterface",
                "ec2:DeleteNetworkInterface",
                "ec2:DescribeInstances",
                "ec2:DescribeTags",
                "ec2:DescribeNetworkInterfaces",
                "ec2:DescribeInstanceTypes",
                "ec2:DescribeSubnets",
                "ec2:DetachNetworkInterface",
                "ec2:DescribeDhcpOptions",
                "ec2:ModifyNetworkInterfaceAttribute",
                "ec2:UnassignPrivateIpAddresses",
                "ec2:CreateTags",
                "ec2:DescribeRouteTables",
                "ec2:DescribeSecurityGroups",
                "ec2:DescribeVolumes",
                "ec2:DescribeVolumesModifications",
                "ec2:DescribeVpcs"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "eks:Describe*",
                "eks:List*",
                "eks:AssociateAccessPolicy",
                "eks:AccessKubernetesApi",
                "eks-auth:AssumeRoleForPodIdentity"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "elasticloadbalancing:Create*",
                "elasticloadbalancing:Describe*"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "sagemaker:CreateModel",
                "sagemaker:DescribeModel",
                "sagemaker:DeleteModel",
                "sagemaker:ListModels",
                "sagemaker:CreateEndpointConfig",
                "sagemaker:DescribeEndpointConfig",
                "sagemaker:DeleteEndpointConfig",
                "sagemaker:CreateEndpoint",
                "sagemaker:DeleteEndpoint",
                "sagemaker:DescribeEndpoint",
                "sagemaker:UpdateEndpoint",
                "sagemaker:ListTags",
                "sagemaker:EnableClusterInference",
                "sagemaker:DescribeClusterInference",
                "sagemaker:DescribeHubContent"
            ],
            "Resource": "arn:aws:sagemaker:$REGION:*:*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "fsx:DescribeFileSystems"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "acm:ImportCertificate",
                "acm:DeleteCertificate"
            ],
            "Resource": "arn:aws:acm:$REGION:$ACCOUNT_ID:certificate/*"
        },
        {
            "Sid": "AllowPassRoleToSageMaker",
            "Effect": "Allow",
            "Action": [
                "iam:PassRole"
            ],
            "Resource": "arn:aws:iam::$ACCOUNT_ID:role/$HYPERPOD_INFERENCE_ROLE_NAME",
            "Condition": {
                "StringEquals": {
                    "iam:PassedToService": "sagemaker.amazonaws.com"
                }
            }
        },
        {
            "Sid": "CloudWatchEMFPermissions",
            "Effect": "Allow",
            "Action": [
                "cloudwatch:PutMetricData",
                "logs:PutLogEvents",
                "logs:DescribeLogStreams",
                "logs:DescribeLogGroups",
                "logs:CreateLogStream",
                "logs:CreateLogGroup"
            ],
            "Resource": "*"
        }
    ]
}
EOF

Buat Peran eksekusi untuk operator inferensi.

aws iam create-policy --policy-name $HYPERPOD_INFERENCE_ACCESS_POLICY_NAME --policy-document file://permission-policy.json
export policy_arn="arn:aws:iam::${ACCOUNT_ID}:policy/$HYPERPOD_INFERENCE_ACCESS_POLICY_NAME"

# Create the IAM role
eksctl create iamserviceaccount --approve --role-only --name=$HYPERPOD_INFERENCE_SA_NAME --namespace=$HYPERPOD_INFERENCE_SA_NAMESPACE --cluster=$EKS_CLUSTER_NAME --attach-policy-arn=$policy_arn --role-name=$HYPERPOD_INFERENCE_ROLE_NAME --region=$REGION

aws iam create-role --role-name $HYPERPOD_INFERENCE_ROLE_NAME --assume-role-policy-document file://trust-policy.json
 
aws iam put-role-policy --role-name $HYPERPOD_INFERENCE_ROLE_NAME --policy-name InferenceOperatorInlinePolicy --policy-document file://permission-policy.json

Unduh dan buat kebijakan IAM yang diperlukan untuk Load Balancer Controller untuk mengelola Application AWS Load Balancers dan Network Load Balancer di kluster EKS Anda.

%%bash -x 

export ALBController_IAM_POLICY_NAME=HyperPodInferenceALBControllerIAMPolicy

curl -o AWSLoadBalancerControllerIAMPolicy.json https://raw.githubusercontent.com/kubernetes-sigs/aws-load-balancer-controller/v2.13.0/docs/install/iam_policy.json
aws iam create-policy --policy-name $ALBController_IAM_POLICY_NAME --policy-document file://AWSLoadBalancerControllerIAMPolicy.json

Buat akun layanan IAM yang menautkan akun layanan Kubernetes dengan kebijakan IAM, memungkinkan Load AWS Balancer Controller untuk mengambil izin yang AWS diperlukan melalui IRSA (IAM Roles for Service Accounts).

%%bash -x 

export ALB_POLICY_ARN="arn:aws:iam::$ACCOUNT_ID:policy/$ALBController_IAM_POLICY_NAME"

# Create IAM service account with gathered values
eksctl create iamserviceaccount \
  --approve \
  --override-existing-serviceaccounts \
  --name=aws-load-balancer-controller \
  --namespace=kube-system \
  --cluster=$EKS_CLUSTER_NAME \
  --attach-policy-arn=$ALB_POLICY_ARN \
  --region=$REGION

# Print the values for verification
echo "Cluster Name: $EKS_CLUSTER_NAME"
echo "Region: $REGION"
echo "Policy ARN: $ALB_POLICY_ARN"

Terapkan Tags (kubernetes.io.role/elb) ke semua subnet di kluster EKS (baik publik maupun pribadi).

export VPC_ID=$(aws --region $REGION eks describe-cluster --name $EKS_CLUSTER_NAME --query 'cluster.resourcesVpcConfig.vpcId' --output text)

# Add Tags
aws ec2 describe-subnets \
  --filters "Name=vpc-id,Values=${VPC_ID}" "Name=map-public-ip-on-launch,Values=true" \
  --query 'Subnets[*].SubnetId' --output text | \
tr '\t' '\n' | \
xargs -I{} aws ec2 create-tags --resources {} --tags Key=kubernetes.io/role/elb,Value=1

# Verify Tags are added
aws ec2 describe-subnets \
  --filters "Name=vpc-id,Values=${VPC_ID}" "Name=map-public-ip-on-launch,Values=true" \
  --query 'Subnets[*].SubnetId' --output text | \
  tr '\t' '\n' |
xargs -n1 -I{} aws ec2 describe-tags --filters "Name=resource-id,Values={}" "Name=key,Values=kubernetes.io/role/elb" --query "Tags[0].Value" --output text

Buat Namespace untuk KEDA dan Cert Manager.

kubectl create namespace keda
kubectl create namespace cert-manager

Buat VPC Endpoint Amazon S3.

aws ec2 create-vpc-endpoint \
  --vpc-id ${VPC_ID} \
  --vpc-endpoint-type Gateway \
  --service-name "com.amazonaws.${REGION}.s3" \
  --route-table-ids $(aws ec2 describe-route-tables --filters "Name=vpc-id,Values=${VPC_ID}" --query 'RouteTables[].Associations[].RouteTableId' --output text | tr ' ' '\n' | sort -u | tr '\n' ' ')

Konfigurasikan akses penyimpanan S3:

(Opsional) Konfigurasikan akses FSx penyimpanan. Buat akun layanan IAM untuk driver Amazon FSx CSI. Akun layanan ini akan digunakan oleh driver FSx CSI untuk berinteraksi dengan FSx layanan Amazon atas nama cluster Anda.

%%bash -x 


eksctl create iamserviceaccount \
  --name fsx-csi-controller-sa \
  --namespace kube-system \
  --cluster $EKS_CLUSTER_NAME \
  --attach-policy-arn arn:aws:iam::aws:policy/AmazonFSxFullAccess \
  --approve \
  --role-name FSXLCSI-${EKS_CLUSTER_NAME}-${REGION} \
  --region $REGION

Buat kebijakan kepercayaan dan kebijakan izin.

# Create trust policy
cat <<EOF > /tmp/keda-trust-policy.json
{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Principal": {
                "Federated": "arn:aws:iam::$ACCOUNT_ID:oidc-provider/oidc.eks.$REGION.amazonaws.com/id/$OIDC_ID"
            },
            "Action": "sts:AssumeRoleWithWebIdentity",
            "Condition": {
                "StringLike": {
                    "oidc.eks.$REGION.amazonaws.com/id/$OIDC_ID:sub": "system:serviceaccount:kube-system:keda-operator",
                    "oidc.eks.$REGION.amazonaws.com/id/$OIDC_ID:aud": "sts.amazonaws.com"
                }
            }
        }
    ]
}
EOF
 # Create permissions policy
cat <<EOF > /tmp/keda-policy.json
{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": [
                "cloudwatch:GetMetricData",
                "cloudwatch:GetMetricStatistics",
                "cloudwatch:ListMetrics"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "aps:QueryMetrics",
                "aps:GetLabels",
                "aps:GetSeries",
                "aps:GetMetricMetadata"
            ],
            "Resource": "*"
        }
    ]
}
EOF
 # Create the role
aws iam create-role \
    --role-name keda-operator-role \
    --assume-role-policy-document file:///tmp/keda-trust-policy.json
 # Create the policy
KEDA_POLICY_ARN=$(aws iam create-policy \
    --policy-name KedaOperatorPolicy \
    --policy-document file:///tmp/keda-policy.json \
    --query 'Policy.Arn' \
    --output text)
 # Attach the policy to the role
aws iam attach-role-policy \
    --role-name keda-operator-role \
    --policy-arn $KEDA_POLICY_ARN

Jika Anda menggunakan model terjaga keamanannya, buat peran IAM untuk mengakses model yang terjaga keamanannya.

Instal operator HyperPod inferensi. Langkah ini mengumpulkan pengidentifikasi AWS sumber daya yang diperlukan dan menghasilkan perintah instalasi Helm dengan parameter konfigurasi yang sesuai.

Akses bagan helm dari https://github.com/aws/sagemaker-hyperpod-cli/tree/main/helm_chart.

git clone https://github.com/aws/sagemaker-hyperpod-cli
cd sagemaker-hyperpod-cli
cd helm_chart/HyperPodHelmChart

%%bash -x

HYPERPOD_INFERENCE_ROLE_ARN=$(aws iam get-role --role-name=$HYPERPOD_INFERENCE_ROLE_NAME --query "Role.Arn" --output text)
echo $HYPERPOD_INFERENCE_ROLE_ARN
 
S3_CSI_ROLE_ARN=$(aws iam get-role --role-name=$S3_CSI_ROLE_NAME --query "Role.Arn" --output text)
echo $S3_CSI_ROLE_ARN

HYPERPOD_CLUSTER_ARN=$(aws sagemaker describe-cluster --cluster-name $HYPERPOD_CLUSTER_NAME --query "ClusterArn")

# Verify values
echo "Cluster Name: $EKS_CLUSTER_NAME"
echo "Execution Role: $HYPERPOD_INFERENCE_ROLE_ARN"
echo "Hyperpod ARN: $HYPERPOD_CLUSTER_ARN"
# Run the the HyperPod inference operator installation. 

helm install hyperpod-inference-operator charts/inference-operator
-n kube-system \
--set region=$REGION \
 --set eksClusterName=$EKS_CLUSTER_NAME \
--set hyperpodClusterArn=$HYPERPOD_CLUSTER_ARN \
--set executionRoleArn=$HYPERPOD_INFERENCE_ROLE_ARN \
--set s3.serviceAccountRoleArn=$S3_CSI_ROLE_ARN \
--set s3.node.serviceAccount.create=false \
--set keda.podIdentity.aws.irsa.roleArn="arn:aws:iam::$ACCOUNT_ID:role/keda-operator-role" \
--set tlsCertificateS3Bucket="s3://$BUCKET_NAME" \
--set alb.region=$REGION \
--set alb.clusterName=$EKS_CLUSTER_NAME \
--set alb.vpcId=$VPC_ID
 
# For JumpStart Gated Model usage, Add
# --set jumpstartGatedModelDownloadRoleArn=$UMPSTART_GATED_ROLE_ARN

Konfigurasikan anotasi akun layanan untuk integrasi IAM. Anotasi ini memungkinkan akun layanan operator untuk mengasumsikan izin IAM yang diperlukan untuk mengelola titik akhir inferensi dan berinteraksi dengan layanan. AWS

%%bash -x 

EKS_CLUSTER_ROLE_NAME=$(echo $EKS_CLUSTER_ROLE | sed 's/.*\///')

# Annotate service account
kubectl annotate serviceaccount hyperpod-inference-operator-controller-manager \
  -n hyperpod-inference-system \
  eks.amazonaws.com/role-arn=arn:aws:iam::${ACCOUNT_ID}:role/${EKS_CLUSTER_ROLE_NAME} \
  --overwrite

Buat file konfigurasi penerapan model. Ini membuat file manifes Kubernetes yang mendefinisikan penerapan JumpStart model untuk operator inferensi. HyperPod Konfigurasi menentukan cara menerapkan model pra-terlatih dari Amazon SageMaker JumpStart sebagai titik akhir inferensi di kluster Amazon EKS Anda.

cat <<EOF>> simple_model_install.yaml
---
apiVersion: inference.sagemaker.aws.amazon.com/v1alpha1
kind: JumpStartModel
metadata:
  name: testing-deployment-bert
  namespace: default
spec:
  model:
    modelId: "huggingface-eqa-bert-base-cased"
  sageMakerEndpoint:
    name: "hp-inf-ep-for-testing"
  server:
    instanceType: "ml.c5.2xlarge"
  environmentVariables:
    - name: SAMPLE_ENV_VAR
      value: "sample_value"
  maxDeployTimeInSeconds: 1800
EOF

Terapkan model dan bersihkan file konfigurasi. Langkah ini membuat sumber daya JumpStart model dan menghapus file konfigurasi sementara untuk mempertahankan ruang kerja yang bersih.

%%bash -x 

kubectl create -f simple_model_install.yaml
rm -rfv simple_model_install.yaml

Periksa apakah model diinstal dan berjalan. Verifikasi ini memastikan bahwa operator dapat berhasil mengasumsikan AWS izin untuk mengelola titik akhir inferensi.

%%bash

# Get the service account details
kubectl get serviceaccount -n hyperpod-inference-system

# Check if the service account has the AWS annotations
kubectl describe serviceaccount hyperpod-inference-operator-controller-manager -n hyperpod-inference-system

Tulis file input model. Ini membuat file input JSON yang berisi data sampel untuk menguji kemampuan menjawab pertanyaan model yang diterapkan.

%%writefile demo-input.json
{"question" :"what is the name of the planet?","context" : "earth"}

Panggil SageMaker titik akhir untuk melakukan pengujian beban untuk memvalidasi kinerja dan keandalan titik akhir inferensi.

%%bash

#!/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