Merge pull request #144 from Hanchenli/main

[Deploy WIP] Modified the EKS tutorial
vllm-project · Feb 17, 2025 · b6b9f68 · b6b9f68
2 parents 639edc0 + 3eb259e
commit b6b9f68
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 9 deletions.
diff --git 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
@@ -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
@@ -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
@@ -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