[Docs] Add volcano engine startup docs and quick start (#1725)

Jeffwan · web-flow · commit 941e68f221fd · 2025-11-04T08:35:13.000+08:00
Add volcano engine startup docs and quick start

Signed-off-by: Jiaxin Shan &lt;seedjeffwan@gmail.com&gt;
diff --git a/dist/chart/values.yaml b/dist/chart/values.yaml
@@ -86,7 +86,7 @@ gpuOptimizer:
   imagePullSecrets: []
   container:
     image:
-      repository: aibrix/runtime
+      repository: aibrix/metadata-service
       tag: nightly
     resources:
       limits:
diff --git a/dist/chart/vke.yaml b/dist/chart/vke.yaml
@@ -7,8 +7,8 @@ controllerManager:
   imagePullSecrets: []
   container:
     image:
-      repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/controller-manager
-      tag: v0.4.1
+      repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/controller-manager
+      tag: v0.5.0-rc.2
       imagePullPolicy: IfNotPresent
     resources:
       limits:
@@ -38,12 +38,12 @@ gatewayPlugin:
   imagePullSecrets: []
   initContainer:
     image:
-      repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/busybox
+      repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/busybox
       tag: stable
   container:
     image:
-      repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/gateway-plugins
-      tag: v0.4.1
+      repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/gateway-plugins
+      tag: v0.5.0-rc.2
       imagePullPolicy: IfNotPresent
     resources:
       limits:
@@ -71,8 +71,8 @@ gpuOptimizer:
   imagePullSecrets: []
   container:
     image:
-      repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/runtime
-      tag: v0.4.1
+      repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/runtime
+      tag: v0.5.0-rc.2
     resources:
       limits:
         cpu: 500m
@@ -93,7 +93,7 @@ gateway:
     tolerations: []
     container:
       envoy:
-        image: aibrix-container-registry-cn-beijing.cr.volces.com/envoyproxy/envoy:v1.33.2
+        image: aibrix-public-release-cn-beijing.cr.volces.com/envoyproxy/envoy:v1.33.2
         resources:
           requests:
             cpu: "1"
@@ -102,7 +102,7 @@ gateway:
             cpu: "1"
             memory: 1Gi
       shutdownManager:
-        image: aibrix-container-registry-cn-beijing.cr.volces.com/envoyproxy/gateway:v1.2.8
+        image: aibrix-public-release-cn-beijing.cr.volces.com/envoyproxy/gateway:v1.2.8
         resources:
           requests:
             cpu: 10m
@@ -122,12 +122,12 @@ metadata:
     imagePullSecrets: []
     initContainer:
       image:
-        repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/busybox
+        repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/busybox
         tag: stable
     container:
       image:
-        repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/metadata-service
-        tag: v0.4.1
+        repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/metadata-service
+        tag: v0.5.0-rc.2
         imagePullPolicy: IfNotPresent
       resources:
         limits:
@@ -146,7 +146,7 @@ metadata:
     imagePullSecrets: []
     container:
       image:
-        repository: aibrix-container-registry-cn-beijing.cr.volces.com/aibrix/redis
+        repository: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/redis
         tag: "7.4"
       resources:
         requests:
diff --git a/docs/source/getting_started/installation/vke.rst b/docs/source/getting_started/installation/vke.rst
@@ -0,0 +1,75 @@
+.. _vke:
+
+==============
+Volcano Engine
+==============
+
+Introduction
+------------
+
+This doc deploys AIBrix in Volcano Engine Kubernetes Engine.
+
+Steps
+-----
+
+AIBrix Installation
+~~~~~~~~~~~~~~~~~~~
+
+1. Assume you already have VKE cluster up and running
+2. Install AIBrix on VKE
+
+.. code-block:: console
+
+    kubectl apply -k config/overlays/vke/dependency --server-side
+
+    helm install aibrix dist/chart -f dist/chart/vke.yaml -n aibrix-system --create-namespace
+
+3. Wait for components to complete running.
+
+Download Model in TOS
+~~~~~~~~~~~~~~~~~~~~~
+
+Download models in TOS and create the credential in the cluster.
+
+.. code-block:: console
+
+    kubectl create secret generic tos-credential --from-literal=TOS_ACCESS_KEY=<YOUR_ACCESS_KEY> --from-literal=TOS_SECRET_KEY=<YOUR_SECRET_KEY>
+
+
+Deploy base model
+~~~~~~~~~~~~~~~~~
+
+Save yaml as `model.yaml` and run `kubectl apply -f model.yaml`.
+
+.. literalinclude:: ../../../../samples/quickstart/vke/model.yaml
+   :language: yaml
+
+Deploy Prefill-Decode (PD) Disaggregation Model
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Save yaml as `pd-model.yaml` and run `kubectl apply -f pd-model.yaml`.
+
+.. literalinclude:: ../../../../samples/quickstart/vke/pd-model.yaml
+   :language: yaml
+
+
+Inference
+~~~~~~~~~
+
+Once the model is ready and running, you can test it by running:
+
+.. code-block:: bash
+
+    LB_IP=$(kubectl get svc/envoy-aibrix-system-aibrix-eg-903790dc -n envoy-gateway-system -o=jsonpath='{.status.loadBalancer.ingress[0].ip}')
+    ENDPOINT="${LB_IP}:80"
+
+    curl http://${ENDPOINT}/v1/chat/completions \
+      -H "Content-Type: application/json" \
+      -H "routing-strategy: random" \ # change to `pd` if you deployed in disaggregation mode
+      -d '{
+          "model": "deepseek-r1-distill-llama-8b",
+          "messages": [
+              {"role": "system", "content": "You are a helpful assistant."},
+              {"role": "user", "content": "help me write a random generator in python"}
+          ]
+      }'
diff --git a/hack/release/sync-dependency-images.sh b/hack/release/sync-dependency-images.sh
@@ -12,7 +12,7 @@ TARGET_REGISTRY=$1
 
 # List of images to sync in the format "source_image:tag new_repo_path"
 IMAGES=(
-    "redis:latest ${TARGET_REGISTRY}/aibrix/redis:latest"
+    "redis:7.4 ${TARGET_REGISTRY}/aibrix/redis:7.4"
     "envoyproxy/envoy:v1.33.2 ${TARGET_REGISTRY}/aibrix/envoy:v1.33.2"
     "envoyproxy/gateway:v1.2.8 ${TARGET_REGISTRY}/aibrix/gateway:v1.2.8"
     "aibrix/kuberay-operator:v1.2.1-patch-20250726 ${TARGET_REGISTRY}/aibrix/kuberay-operator:v1.2.1-patch-20250726"
diff --git a/samples/quickstart/vke/model.yaml b/samples/quickstart/vke/model.yaml
@@ -0,0 +1,121 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: deepseek-r1-distill-llama-8b
+  labels:
+    model.aibrix.ai/name: deepseek-r1-distill-llama-8b
+    model.aibrix.ai/port: "8000"
+spec:
+  replicas: 1
+  strategy:
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 1
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      model.aibrix.ai/name: deepseek-r1-distill-llama-8b
+  template:
+    metadata:
+      labels:
+        model.aibrix.ai/name: deepseek-r1-distill-llama-8b
+      annotations:
+        prometheus.io/path: "/metrics"
+        prometheus.io/port: "8000"
+        prometheus.io/scrape: "true"
+    spec:
+      initContainers:
+        - command:
+            - aibrix_download
+            - --model-uri
+            - tos://aibrix-artifact-testing/models/DeepSeek-R1-Distill-Llama-8B/
+            - --local-dir
+            - /models/
+          env:
+            - name: DOWNLOADER_NUM_CONNECTIONS
+              value: "16"
+            - name: DOWNLOADER_NUM_THREADS
+              value: "16"
+            - name: DOWNLOADER_ALLOW_FILE_SUFFIX
+              value: json, safetensors
+            - name: TOS_ACCESS_KEY
+              valueFrom:
+                secretKeyRef:
+                  key: TOS_ACCESS_KEY
+                  name: tos-credential
+            - name: TOS_SECRET_KEY
+              valueFrom:
+                secretKeyRef:
+                  key: TOS_SECRET_KEY
+                  name: tos-credential
+            - name: TOS_ENDPOINT
+              value: https://tos-s3-cn-beijing.ivolces.com
+            - name: TOS_REGION
+              value: cn-beijing
+          image: aibrix-public-release-cn-beijing.cr.volces.com/aibrix/runtime:v0.5.0-rc.2
+          name: init-model
+          volumeMounts:
+            - mountPath: /models
+              name: model-hostpath
+      containers:
+        - name: vllm-openai
+          image: aibrix-public-release-cn-beijing.cr.volces.com/vllm/vllm-openai:0.11.0
+          imagePullPolicy: Always
+          command:
+            - python3
+            - -m
+            - vllm.entrypoints.openai.api_server
+            - --port
+            - "8000"
+            - --uvicorn-log-level
+            - warning
+            - --model
+            - /models/DeepSeek-R1-Distill-Llama-8B/
+            - --trust-remote-code
+            - --served-model-name
+            - deepseek-r1-distill-llama-8b
+            - --disable-fastapi-docs
+          volumeMounts:
+            - mountPath: /models
+              name: model-hostpath
+          resources:
+            limits:
+              nvidia.com/gpu: "1"
+              cpu: "12"
+              memory: "48G"
+            requests:
+              nvidia.com/gpu: "1"
+              cpu: "12"
+              memory: "48G"
+      volumes:
+        - name: model-hostpath
+          hostPath:
+            path: /root/models
+            type: DirectoryOrCreate
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    model.aibrix.ai/name: deepseek-r1-distill-llama-8b
+    prometheus-discovery: "true"
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/port: "8080"
+  name: deepseek-r1-distill-llama-8b # Note: The Service name must match the label value `model.aibrix.ai/name` in the Deployment
+  namespace: default
+spec:
+  ports:
+    - name: serve
+      port: 8000
+      protocol: TCP
+      targetPort: 8000
+    - name: http
+      port: 8080
+      protocol: TCP
+      targetPort: 8080
+  selector:
+    model.aibrix.ai/name: deepseek-r1-distill-llama-8b
+  type: ClusterIP
diff --git a/samples/quickstart/vke/pd-model.yaml b/samples/quickstart/vke/pd-model.yaml
