feat: add vllm-api-key

Signed-off-by: kbvd623 <[email protected]>
vllm-project · Mar 4, 2025 · f339947 · f339947
1 parent fd56e78
commit f339947
Show file tree

Hide file tree

Showing 10 changed files with 515 additions and 63 deletions.
diff --git a/.github/curl-05-secure-vllm.sh b/.github/curl-05-secure-vllm.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+VLLM_API_KEY=abc123XYZ987
+
+# Curl and save output
+OUTPUT_DIR="output-05-secure-vllm"
+[ ! -d "$OUTPUT_DIR" ] && mkdir $OUTPUT_DIR
+chmod -R 777 $OUTPUT_DIR
+
+# shellcheck disable=SC2034  # result_model appears unused. Verify it or export it.
+# Fetch model list with authentication
+curl -s -H "Authorization: Bearer $VLLM_API_KEY" "http://$HOST:$PORT/v1/models" | tee "$OUTPUT_DIR/models-05-secure-vllm.json"
+
+# Run completion query with authentication
+curl -s -X POST -H "Authorization: Bearer $VLLM_API_KEY" \
+     -H "Content-Type: application/json" \
+     -d '{"model": "facebook/opt-125m", "prompt": "Once upon a time,", "max_tokens": 10}' \
+     "http://$HOST:$PORT/v1/completions" | tee "$OUTPUT_DIR/query-05-secure-vllm.json"
diff --git a/.github/values-05-secure-vllm.yaml b/.github/values-05-secure-vllm.yaml
@@ -0,0 +1,19 @@
+servingEngineSpec:
+  runtimeClassName: ""
+  vllmApiKey: "abc123XYZ987"
+  modelSpec:
+  - name: "opt125m"
+    repository: "vllm/vllm-openai"
+    tag: "latest"
+    modelURL: "facebook/opt-125m"
+
+    replicaCount: 1
+
+    requestCPU: 6
+    requestMemory: "16Gi"
+    requestGPU: 1
+
+routerSpec:
+  repository: "localhost:5000/git-act-router"
+  imagePullPolicy: "IfNotPresent"
+  enableRouter: true
diff --git a/.github/workflows/functionality-helm-chart.yml b/.github/workflows/functionality-helm-chart.yml
@@ -52,7 +52,41 @@ jobs:
             sudo helm uninstall vllm
         if: always()
       - run: echo "🍏 This job's status is ${{ job.status }}."
-
+  Secure-Minimal-Example:
+    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
+        env:
+          DOCKER_BUILDKIT: 1
+        run: |
+          cd ${{ github.workspace }}
+          sudo docker build -t localhost:5000/git-act-router -f docker/Dockerfile .
+          sudo docker push localhost:5000/git-act-router
+          sudo sysctl fs.protected_regular=0
+          sudo minikube image load localhost:5000/git-act-router
+          sudo helm install vllm ./helm -f .github/values-05-secure-vllm.yaml
+      - name: Validate the installation and send query to the stack
+        run: |
+          sudo bash .github/port-forward.sh curl-05-secure-vllm
+        timeout-minutes: 2
+      - name: Archive functionality results
+        uses: actions/upload-artifact@v4
+        with:
+          name: output-05-secure-vllm
+          path: |
+            output-05-secure-vllm/
+      - name: Helm uninstall
+        run: |
+            sudo helm uninstall vllm
+        if: always()
+      - run: echo "🍏 This job's status is ${{ job.status }}."
   Two-Pods-Minimal-Example:
     runs-on: self-hosted
     needs: Minimal-Example

diff --git a/helm/templates/deployment-router.yaml b/helm/templates/deployment-router.yaml
@@ -22,6 +22,22 @@ spec:
       - name: router-container
         image: "{{ .Values.routerSpec.repository | default "lmcache/lmstack-router" }}:{{ .Values.routerSpec.tag | default "latest" }}"
         imagePullPolicy: "{{ .Values.routerSpec.imagePullPolicy | default "Always" }}"
+        env:
+          {{- $vllmApiKey := $.Values.servingEngineSpec.vllmApiKey }}
+          {{- if $vllmApiKey }}
+          - name: VLLM_API_KEY
+            {{- if kindIs "string" $vllmApiKey }}
+            valueFrom:
+              secretKeyRef:
+                name: {{ .Release.Name }}-secrets
+                key: vllmApiKey
+            {{- else }}
+            valueFrom:
+              secretKeyRef:
+                name: {{ $vllmApiKey.secretName }}
+                key: {{ $vllmApiKey.secretKey }}
+            {{- end }}
+          {{- end }}
         args:
           - "--host"
           - "0.0.0.0"

diff --git a/helm/templates/deployment-vllm-multi.yaml b/helm/templates/deployment-vllm-multi.yaml
@@ -93,6 +93,21 @@ spec:
                 key: {{ $modelSpec.hf_token.secretKey }}
             {{- end }}
           {{- end }}
+          {{- $vllmApiKey := $.Values.servingEngineSpec.vllmApiKey }}
+          {{- if $vllmApiKey }}
+          - name: VLLM_API_KEY
+            {{- if kindIs "string" $vllmApiKey }}
+            valueFrom:
+              secretKeyRef:
+                name: {{ .Release.Name }}-secrets
+                key: vllmApiKey
+            {{- else }}
+            valueFrom:
+              secretKeyRef:
+                name: {{ $vllmApiKey.secretName }}
+                key: {{ $vllmApiKey.secretKey }}
+            {{- end }}
+          {{- end }}
           {{- with $modelSpec.env }}
           {{- toYaml . | nindent 10 }}
           {{- end }}

diff --git a/helm/templates/secrets.yaml b/helm/templates/secrets.yaml
@@ -5,6 +5,11 @@ metadata:
   namespace: {{ .Release.Namespace }}
 type: Opaque
 data:
+  {{- $vllmApiKey := $.Values.servingEngineSpec.vllmApiKey }}
+  {{- if and $vllmApiKey (kindIs "string" $vllmApiKey) }}
+  vllmApiKey: {{ $vllmApiKey | b64enc | quote }}
+  {{- end }}
+
   {{- range $modelSpec := .Values.servingEngineSpec.modelSpec }}
   {{- with $ -}}
   {{-   if and $modelSpec.hf_token (kindIs "string" $modelSpec.hf_token) }}