[CI/CD] Functionality test for helm chart (#30)

Signed-off-by: Shaoting Feng <shaotingf@uchicago.edu>

Author: Shaoting-Feng

.github/port-forward.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+# Ensure the script is run with root privileges
+if [[ $EUID -ne 0 ]]; then
+   echo "This script must be run as root (use sudo)."
+   exit 1
+fi
+
+echo "Waiting for all llmstack pods to be in Running state..."
+
+# Loop to check if all llmstack-related pods are in the Running state
+while true; do
+    # Get all pods containing "vllm" in their name and extract their STATUS column
+    pod_status=$(sudo kubectl get pods --no-headers | grep "vllm" | awk '{print $3}' | sort | uniq)
+    pod_ready=$(sudo kubectl get pods --no-headers | grep "vllm" | awk '{print $2}' | sort | uniq)
+
+    # If the only unique status is "Running", break the loop and continue
+    if [[ "$pod_status" == "Running" ]] && [[ "$pod_ready" == "1/1" ]]; then
+        echo "All llmstack pods are now Ready and in Running state."
+        break
+    fi
+
+    echo "Not all pods are ready yet. Checking again in 5 seconds..."
+    sleep 5
+done
+
+# Expose router service
+sudo kubectl patch service vllm-router-service -p '{"spec":{"type":"NodePort"}}'
+ip=$(sudo minikube ip)
+port=$(sudo kubectl get svc vllm-router-service -o=jsonpath='{.spec.ports[0].nodePort}')
+
+# Curl and save output
+[ ! -d "output" ] && mkdir output
+chmod -R 777 output
+result_model=$(curl -s http://$ip:$port/models | tee output/models.json)
+result_query=$(curl -X POST http://$ip:$port/completions -H "Content-Type: application/json" -d '{"model": "facebook/opt-125m", "prompt": "Once upon a time,", "max_tokens": 10}' | tee output/query.json)

.github/workflows/functionality-helm-chart.yml

@@ -0,0 +1,46 @@
+name: Functionality test for helm chart
+run-name: ${{ github.actor }} is testing out helm chart functions 🚀
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - '.github/workflows/**'
+      - '**.py'
+      - 'setup.py'
+  pull_request:
+    paths:
+        - '.github/workflows/**'
+        - '**.py'
+        - 'setup.py'
+  merge_group:
+jobs:
+  Check-Health-of-Cluster:
+    runs-on: self-hosted
+    steps:
+      - run: echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
+      - run: echo "🐧 This job is now running on a ${{ runner.os }} server hosted by GitHub!"
+      - run: echo "🔎 The name of your branch is ${{ github.ref }} and your repository is ${{ github.repository }}."
+      - name: Check out repository code
+        uses: actions/checkout@v4
+      - run: echo "💡 The ${{ github.repository }} repository has been cloned to the runner."
+      - run: echo "🖥️ The workflow is now ready to test your code on the runner."
+      - name: Deploy via helm charts
+        run: |
+          cd ${{ github.workspace }}
+          sudo helm repo add vllm https://vllm-project.github.io/production-stack
+          sudo helm install vllm vllm/vllm-stack -f tutorials/assets/values-01-minimal-example.yaml
+      - name: Validate the installation and send query to the stack
+        run: |
+          sudo bash .github/port-forward.sh
+      - name: Archive functionality results
+        uses: actions/upload-artifact@v4
+        with:
+          name: curl-models-query
+          path: |
+            output/
+      - name: Helm uninstall
+        run: |
+           sudo helm uninstall vllm
+        if: always()
+      - run: echo "🍏 This job's status is ${{ job.status }}."