diff --git a/deployment_on_cloud/aws/production_stack_specification.yaml b/deployment_on_cloud/aws/production_stack_specification.yaml index b0f45aaf..4e049228 100644 --- a/deployment_on_cloud/aws/production_stack_specification.yaml +++ b/deployment_on_cloud/aws/production_stack_specification.yaml @@ -15,4 +15,4 @@ servingEngineSpec: pvcStorage: "40Gi" pvcAccessMode: - ReadWriteMany - storageClass: "efs_static_storage_class_indicator" #This is to let helm pvc know it should be empty string + storageClass: "" #This is to let helm pvc know it should be empty string diff --git a/helm/Chart.yaml b/helm/Chart.yaml index 9fdc5798..0f6a3789 100644 --- a/helm/Chart.yaml +++ b/helm/Chart.yaml @@ -15,7 +15,7 @@ type: application # This is the chart version. This version number should be incremented each time you make changes # to the chart and its templates, including the app version. # Versions are expected to follow Semantic Versioning (https://semver.org/) -version: 0.0.6 +version: 0.0.7 maintainers: - name: apostac diff --git a/helm/templates/pvc.yaml b/helm/templates/pvc.yaml index 7042ff24..29513788 100644 --- a/helm/templates/pvc.yaml +++ b/helm/templates/pvc.yaml @@ -15,12 +15,8 @@ spec: resources: requests: storage: {{ $modelSpec.pvcStorage | default "20Gi" }} # Default to 40Gi if not set - {{- if $modelSpec.storageClass }} - {{- if eq $modelSpec.storageClass "efs_static_storage_class_indicator" }} - storageClassName: "" - {{- else }} - storageClassName: "{{ $modelSpec.storageClass }}" - {{- end }} + {{- if hasKey $modelSpec "storageClass" }} + storageClassName: "{{ $modelSpec.storageClass }}" {{- end }} {{- if not (empty $modelSpec.pvcMatchLabels) }} selector: diff --git a/tutorials/deployments/01-AWS-EKS-deployment.md b/tutorials/deployments/01-AWS-EKS-deployment.md index 2508b3c2..d3b5e4aa 100644 --- a/tutorials/deployments/01-AWS-EKS-deployment.md +++ b/tutorials/deployments/01-AWS-EKS-deployment.md @@ -2,7 +2,7 @@ This guide walks you through the script that sets up a vLLM production-stack on top of EKS on AWS. It includes how the script configures Elastic File System (EFS) for persistent volume, setting the security groups, and deploying a production AI inference stack using Helm. -## Prerequisites +## Installing Prerequisites Before running this setup, ensure you have: @@ -11,6 +11,20 @@ Before running this setup, ensure you have: 3. Kubectl 4. Helm +## TLDR + +To run the service + +```bash +bash entry_point.sh YOUR_AWSREGION EXAMPLE_YAML_PATH +``` + +Clean up the service (not including VPC) with: + +```bash +bash clean_up.sh production-stack YOUR_AWSREGION +``` + ## Step by Step Explanation ### Step 1: Deploy the EKS Cluster @@ -202,6 +216,7 @@ servingEngineSpec: pvcStorage: "40Gi" pvcAccessMode: - ReadWriteMany + storageClass: "" ``` ### Step 7 Stopping the Helm Cluster