diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 9e13098f6..6db093e0e 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -8,6 +8,7 @@ repos:
       # list of supported hooks: https://pre-commit.com/hooks.html
       - id: check-yaml
         args: ["--unsafe"]
+        exclude: "examples/online_serving/chart-helm/templates/"
       - id: debug-statements
       - id: end-of-file-fixer
       - id: mixed-line-ending
diff --git a/examples/online_serving/chart-helm/.helmignore b/examples/online_serving/chart-helm/.helmignore
new file mode 100644
index 000000000..6ad16c568
--- /dev/null
+++ b/examples/online_serving/chart-helm/.helmignore
@@ -0,0 +1,6 @@
+*.png
+.git/
+ct.yaml
+lintconf.yaml
+values.schema.json
+/workflows
diff --git a/examples/online_serving/chart-helm/Chart.yaml b/examples/online_serving/chart-helm/Chart.yaml
new file mode 100644
index 000000000..974eee93c
--- /dev/null
+++ b/examples/online_serving/chart-helm/Chart.yaml
@@ -0,0 +1,15 @@
+apiVersion: v2
+name: chart-vllm-omni
+description: A Helm chart for deploying vLLM-Omni on Kubernetes for omni-modality model serving
+
+# Application chart that can be packaged and deployed
+type: application
+
+# Chart version - increment on each change to the chart
+version: 0.1.0
+
+# vllm-omni application version — keep in sync with image.tag in values.yaml
+appVersion: "0.16.0"
+
+maintainers:
+  - name: vllm-omni-team
diff --git a/examples/online_serving/chart-helm/README.md b/examples/online_serving/chart-helm/README.md
new file mode 100644
index 000000000..a3b413a35
--- /dev/null
+++ b/examples/online_serving/chart-helm/README.md
@@ -0,0 +1,144 @@
+# vLLM-Omni Helm Chart
+
+Helm chart for deploying [vLLM-Omni](https://github.com/vllm-project/vllm-omni) on Kubernetes. vLLM-Omni extends vLLM with omni-modality model serving, supporting text-to-image, multimodal chat, text-to-speech, and more.
+
+## Prerequisites
+
+- Kubernetes 1.24+
+- Helm 3.x
+- NVIDIA GPU nodes with [NVIDIA Device Plugin](https://github.com/NVIDIA/k8s-device-plugin)
+
+## Quick Start
+
+```bash
+helm install my-release ./chart-helm \
+  --set model=Tongyi-MAI/Z-Image-Turbo
+```
+
+## Configuration
+
+### Model Selection
+
+Set the `model` value to any supported HuggingFace model ID:
+
+| Model | Type | GPUs | Notes |
+|-------|------|------|-------|
+| `Tongyi-MAI/Z-Image-Turbo` | text-to-image | 1 | Small, fast (default) |
+| `stabilityai/stable-diffusion-3.5-medium` | text-to-image | 1 | ~6GB VRAM |
+| `Qwen/Qwen-Image` | text-to-image | 1 | Large, ~40GB+ VRAM |
+| `Qwen/Qwen2.5-Omni-7B` | multimodal | 2 | Text + audio + image + video |
+| `Qwen/Qwen3-Omni-7B-Chat` | multimodal | 2 | Latest omni model |
+| `Qwen/Qwen3-TTS` | text-to-speech | 1 | TTS |
+
+### HuggingFace Token
+
+For gated models that require authentication:
+
+```bash
+helm install my-release ./chart-helm \
+  --set model=Qwen/Qwen2.5-Omni-7B \
+  --set hfToken=hf_xxxxx \
+  --set resources.requests."nvidia\.com/gpu"=2 \
+  --set resources.limits."nvidia\.com/gpu"=2
+```
+
+### Omni-Specific Flags
+
+Enable VAE memory optimizations for diffusion models:
+
+```bash
+helm install my-release ./chart-helm \
+  --set model=Qwen/Qwen-Image \
+  --set omniArgs.vaeUseSlicing=true \
+  --set omniArgs.vaeUseTiling=true
+```
+
+Enable CPU offloading:
+
+```bash
+helm install my-release ./chart-helm \
+  --set model=Qwen/Qwen-Image \
+  --set omniArgs.enableCpuOffload=true
+```
+
+Pass additional raw CLI flags:
+
+```bash
+helm install my-release ./chart-helm \
+  --set model=Qwen/Qwen-Image \
+  --set omniArgs.extraArgs[0]="--enable-layerwise-offload"
+```
+
+### Model Cache
+
+By default, a PersistentVolumeClaim is created for the HuggingFace model cache to avoid re-downloading models on pod restarts:
+
+```yaml
+modelCache:
+  enabled: true
+  storageSize: "50Gi"
+  storageClassName: ""
+```
+
+To use an ephemeral volume instead:
+
+```bash
+helm install my-release ./chart-helm \
+  --set modelCache.enabled=false
+```
+
+### Custom Command Override
+
+To fully override the container command:
+
+```bash
+helm install my-release ./chart-helm \
+  --set image.command[0]=vllm \
+  --set image.command[1]=serve \
+  --set image.command[2]=my-model \
+  --set image.command[3]=--omni \
+  --set image.command[4]=--host \
+  --set image.command[5]=0.0.0.0
+```
+
+## API Endpoints
+
+Once deployed, vLLM-Omni exposes the following OpenAI-compatible endpoints:
+
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| `/health` | GET | Health check |
+| `/v1/models` | GET | List available models |
+| `/v1/chat/completions` | POST | Chat completions (text/multimodal) |
+| `/v1/images/generations` | POST | Image generation |
+| `/v1/images/edits` | POST | Image editing |
+| `/v1/audio/speech` | POST | Text-to-speech |
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `Chart.yaml` | Chart metadata (name, version, maintainers) |
+| `values.yaml` | Default configuration values |
+| `values.schema.json` | JSON schema for validating values |
+| `templates/_helpers.tpl` | Helper templates for common configurations |
+| `templates/deployment.yaml` | Kubernetes Deployment |
+| `templates/service.yaml` | Kubernetes Service (ClusterIP) |
+| `templates/secrets.yaml` | Secrets (generic + HuggingFace token) |
+| `templates/pvc.yaml` | PersistentVolumeClaim for model cache |
+| `templates/configmap.yaml` | Optional ConfigMap |
+| `templates/hpa.yaml` | HorizontalPodAutoscaler |
+| `templates/poddisruptionbudget.yaml` | PodDisruptionBudget |
+| `templates/custom-objects.yaml` | Custom Kubernetes objects |
+
+## Running Tests
+
+This chart includes unit tests using [helm-unittest](https://github.com/helm-unittest/helm-unittest). Install the plugin and run tests:
+
+```bash
+# Install plugin
+helm plugin install https://github.com/helm-unittest/helm-unittest
+
+# Run tests
+helm unittest .
+```
diff --git a/examples/online_serving/chart-helm/ct.yaml b/examples/online_serving/chart-helm/ct.yaml
new file mode 100644
index 000000000..157243f9e
--- /dev/null
+++ b/examples/online_serving/chart-helm/ct.yaml
@@ -0,0 +1,3 @@
+chart-dirs:
+  - charts
+validate-maintainers: false
diff --git a/examples/online_serving/chart-helm/lintconf.yaml b/examples/online_serving/chart-helm/lintconf.yaml
new file mode 100644
index 000000000..a63c814d4
--- /dev/null
+++ b/examples/online_serving/chart-helm/lintconf.yaml
@@ -0,0 +1,42 @@
+---
+rules:
+  braces:
+    min-spaces-inside: 0
+    max-spaces-inside: 0
+    min-spaces-inside-empty: -1
+    max-spaces-inside-empty: -1
+  brackets:
+    min-spaces-inside: 0
+    max-spaces-inside: 0
+    min-spaces-inside-empty: -1
+    max-spaces-inside-empty: -1
+  colons:
+    max-spaces-before: 0
+    max-spaces-after: 1
+  commas:
+    max-spaces-before: 0
+    min-spaces-after: 1
+    max-spaces-after: 1
+  comments:
+    require-starting-space: true
+    min-spaces-from-content: 2
+  document-end: disable
+  document-start: disable
+  empty-lines:
+    max: 2
+    max-start: 0
+    max-end: 0
+  hyphens:
+    max-spaces-after: 1
+  indentation:
+    spaces: consistent
+    indent-sequences: whatever
+    check-multi-line-strings: false
+  key-duplicates: enable
+  line-length: disable
+  new-line-at-end-of-file: disable
+  new-lines:
+    type: unix
+  trailing-spaces: enable
+  truthy:
+    level: warning
diff --git a/examples/online_serving/chart-helm/templates/_helpers.tpl b/examples/online_serving/chart-helm/templates/_helpers.tpl
new file mode 100644
index 000000000..00f407bab
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/_helpers.tpl
@@ -0,0 +1,203 @@
+{{/*
+Define the vllm-omni serve command from model + omniArgs.
+If image.command is set, uses that as a full override.
+*/}}
+{{- define "chart.omni-command" -}}
+{{- if .Values.image.command }}
+{{-   toYaml .Values.image.command }}
+{{- else }}
+- "vllm"
+- "serve"
+- {{ .Values.model | quote }}
+- "--omni"
+- "--host"
+- "0.0.0.0"
+- "--port"
+- {{ include "chart.container-port" . | quote }}
+{{- if .Values.omniArgs.vaeUseSlicing }}
+- "--vae-use-slicing"
+{{- end }}
+{{- if .Values.omniArgs.vaeUseTiling }}
+- "--vae-use-tiling"
+{{- end }}
+{{- if .Values.omniArgs.enableCpuOffload }}
+- "--enable-cpu-offload"
+{{- end }}
+{{- if .Values.omniArgs.numGpus }}
+- "--num-gpus"
+- {{ .Values.omniArgs.numGpus | quote }}
+{{- end }}
+{{- if .Values.omniArgs.stageConfigsPath }}
+- "--stage-configs-path"
+- {{ .Values.omniArgs.stageConfigsPath | quote }}
+{{- end }}
+{{- if and .Values.omniArgs.cacheBackend (ne .Values.omniArgs.cacheBackend "none") }}
+- "--cache-backend"
+- {{ .Values.omniArgs.cacheBackend | quote }}
+{{- end }}
+{{- if .Values.omniArgs.defaultSamplingParams }}
+- "--default-sampling-params"
+- {{ .Values.omniArgs.defaultSamplingParams | quote }}
+{{- end }}
+{{- if and .Values.omniArgs.workerBackend (ne .Values.omniArgs.workerBackend "multi_process") }}
+- "--worker-backend"
+- {{ .Values.omniArgs.workerBackend | quote }}
+{{- end }}
+{{- range .Values.omniArgs.extraArgs }}
+- {{ . | quote }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Define HuggingFace environment variables
+*/}}
+{{- define "chart.hf-env" -}}
+- name: HF_HOME
+  value: "/cache/huggingface"
+- name: HOME
+  value: "/cache"
+{{- if .Values.hfToken }}
+- name: HF_TOKEN
+  valueFrom:
+    secretKeyRef:
+      name: {{ .Release.Name }}-hf-token
+      key: token
+{{- end }}
+{{- end }}
+
+{{/*
+Define ports for the pods
+*/}}
+{{- define "chart.container-port" -}}
+{{-  default "8000" .Values.containerPort }}
+{{- end }}
+
+{{/*
+Define service name
+*/}}
+{{- define "chart.service-name" -}}
+{{-  if .Values.serviceName -}}
+{{ .Values.serviceName | lower | trim }}
+{{-  else -}}
+{{ printf "%s-service" .Release.Name }}
+{{-  end -}}
+{{- end }}
+
+{{/*
+Define service port
+*/}}
+{{- define "chart.service-port" -}}
+{{-  if .Values.servicePort }}
+{{-    .Values.servicePort }}
+{{-  else }}
+{{-    include "chart.container-port" . }}
+{{-  end }}
+{{- end }}
+
+{{/*
+Define service port name
+*/}}
+{{- define "chart.service-port-name" -}}
+"service-port"
+{{- end }}
+
+{{/*
+Define container port name
+*/}}
+{{- define "chart.container-port-name" -}}
+"container-port"
+{{- end }}
+
+{{/*
+Define deployment strategy
+*/}}
+{{- define "chart.strategy" -}}
+strategy:
+{{-   if not .Values.deploymentStrategy }}
+  type: Recreate
+{{-   else }}
+{{      toYaml .Values.deploymentStrategy | indent 2 }}
+{{-   end }}
+{{- end }}
+
+{{/*
+Define additional ports
+*/}}
+{{- define "chart.extraPorts" }}
+{{-   with .Values.extraPorts }}
+{{      toYaml . }}
+{{-   end }}
+{{- end }}
+
+{{/*
+Define chart external ConfigMaps and Secrets
+*/}}
+{{- define "chart.externalConfigs" -}}
+{{-   with .Values.externalConfigs -}}
+{{      toYaml . }}
+{{-   end }}
+{{- end }}
+
+{{/*
+Define startup, liveness and readiness probes
+*/}}
+{{- define "chart.probes" -}}
+{{-   if .Values.startupProbe  }}
+startupProbe:
+{{-     with .Values.startupProbe }}
+{{-       toYaml . | nindent 2 }}
+{{-     end }}
+{{-   end }}
+{{-   if .Values.readinessProbe  }}
+readinessProbe:
+{{-     with .Values.readinessProbe }}
+{{-       toYaml . | nindent 2 }}
+{{-     end }}
+{{-   end }}
+{{-   if .Values.livenessProbe  }}
+livenessProbe:
+{{-     with .Values.livenessProbe }}
+{{-       toYaml . | nindent 2 }}
+{{-     end }}
+{{-   end }}
+{{- end }}
+
+{{/*
+Define resources
+*/}}
+{{- define "chart.resources" -}}
+requests:
+  memory: {{ required "Value 'resources.requests.memory' must be defined !" .Values.resources.requests.memory | quote }}
+  cpu: {{ required "Value 'resources.requests.cpu' must be defined !" .Values.resources.requests.cpu | quote }}
+  {{- if and (gt (int (index .Values.resources.requests "nvidia.com/gpu")) 0) (gt (int (index .Values.resources.limits "nvidia.com/gpu")) 0) }}
+  nvidia.com/gpu: {{ required "Value 'resources.requests.nvidia.com/gpu' must be defined !" (index .Values.resources.requests "nvidia.com/gpu") }}
+  {{- end }}
+limits:
+  memory: {{ required "Value 'resources.limits.memory' must be defined !" .Values.resources.limits.memory | quote }}
+  cpu: {{ required "Value 'resources.limits.cpu' must be defined !" .Values.resources.limits.cpu | quote }}
+  {{- if and (gt (int (index .Values.resources.requests "nvidia.com/gpu")) 0) (gt (int (index .Values.resources.limits "nvidia.com/gpu")) 0) }}
+  nvidia.com/gpu: {{ required "Value 'resources.limits.nvidia.com/gpu' must be defined !" (index .Values.resources.limits "nvidia.com/gpu") }}
+  {{- end }}
+{{- end }}
+
+{{/*
+Define user for the main container
+*/}}
+{{- define "chart.user" }}
+{{-   if .Values.image.runAsUser  }}
+runAsUser:
+{{-     with .Values.image.runAsUser }}
+{{-       toYaml . | nindent 2 }}
+{{-     end }}
+{{-   end }}
+{{- end }}
+
+{{/*
+Define chart labels
+*/}}
+{{- define "chart.labels" -}}
+{{-   with .Values.labels -}}
+{{      toYaml . }}
+{{-   end }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/configmap.yaml b/examples/online_serving/chart-helm/templates/configmap.yaml
new file mode 100644
index 000000000..e185c7e0a
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/configmap.yaml
@@ -0,0 +1,11 @@
+{{- if .Values.configs -}}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: "{{ .Release.Name }}-configs"
+  namespace: {{ .Release.Namespace }}
+data:
+  {{- with .Values.configs }}
+  {{- toYaml . | nindent 2 }}
+  {{- end }}
+{{- end -}}
diff --git a/examples/online_serving/chart-helm/templates/custom-objects.yaml b/examples/online_serving/chart-helm/templates/custom-objects.yaml
new file mode 100644
index 000000000..f3b4781c8
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/custom-objects.yaml
@@ -0,0 +1,6 @@
+{{- if .Values.customObjects }}
+{{- range .Values.customObjects }}
+{{- tpl (. | toYaml) $ }}
+---
+{{- end }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/deployment.yaml b/examples/online_serving/chart-helm/templates/deployment.yaml
new file mode 100644
index 000000000..c36f8df00
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/deployment.yaml
@@ -0,0 +1,106 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: "{{ .Release.Name }}-deployment-vllm-omni"
+  namespace: {{ .Release.Namespace }}
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  {{- include "chart.strategy" . | nindent 2 }}
+  selector:
+    matchLabels:
+    {{- include "chart.labels" . | nindent 6 }}
+  progressDeadlineSeconds: 1800
+  template:
+    metadata:
+      labels:
+      {{- include "chart.labels" . | nindent 8 }}
+    spec:
+      containers:
+        - name: "vllm-omni"
+          image: "{{ required "Required value 'image.repository' must be defined !" .Values.image.repository }}:{{ required "Required value 'image.tag' must be defined !" .Values.image.tag }}"
+          command:
+            {{- include "chart.omni-command" . | nindent 12 }}
+          securityContext:
+            {{- if .Values.image.securityContext }}
+              {{- with .Values.image.securityContext }}
+              {{- toYaml . | nindent 12 }}
+              {{- end }}
+            {{- else }}
+            runAsNonRoot: false
+              {{- include "chart.user" . | indent 12 }}
+            {{- end }}
+          imagePullPolicy: IfNotPresent
+          env:
+            {{- include "chart.hf-env" . | nindent 12 }}
+            {{- if .Values.image.env }}
+            {{- toYaml .Values.image.env | nindent 12 }}
+            {{- end }}
+          {{- if or .Values.externalConfigs .Values.configs .Values.secrets }}
+          envFrom:
+            {{- if .Values.configs }}
+            - configMapRef:
+                name: "{{ .Release.Name }}-configs"
+            {{- end }}
+            {{- if .Values.secrets }}
+            - secretRef:
+                name: "{{ .Release.Name }}-secrets"
+            {{- end }}
+            {{- include "chart.externalConfigs" . | nindent 12 }}
+          {{- end }}
+          ports:
+            - name: {{ include "chart.container-port-name" . }}
+              containerPort: {{ include "chart.container-port" . }}
+            {{- include "chart.extraPorts" . | nindent 12 }}
+          {{- include "chart.probes" . | indent 10 }}
+          resources: {{- include "chart.resources" . | nindent 12 }}
+          volumeMounts:
+          - name: shm
+            mountPath: /dev/shm
+          - name: model-cache
+            mountPath: /cache
+
+        {{- with .Values.extraContainers }}
+        {{ toYaml . | nindent 8 }}
+        {{- end }}
+
+      {{- if .Values.extraInit.initContainers }}
+      initContainers:
+        {{- toYaml .Values.extraInit.initContainers | nindent 8 }}
+      {{- end }}
+
+      volumes:
+        - name: shm
+          emptyDir:
+            medium: Memory
+            sizeLimit: {{ .Values.shmSize }}
+        - name: model-cache
+          {{- if .Values.modelCache.enabled }}
+          persistentVolumeClaim:
+            claimName: {{ .Release.Name }}-model-cache
+          {{- else }}
+          emptyDir: {}
+          {{- end }}
+
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- if .Values.gpuModels }}
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                - key: nvidia.com/gpu.product
+                  operator: In
+                  values:
+                    {{- toYaml .Values.gpuModels | nindent 20 }}
+      {{- end }}
diff --git a/examples/online_serving/chart-helm/templates/hpa.yaml b/examples/online_serving/chart-helm/templates/hpa.yaml
new file mode 100644
index 000000000..cadc92ed5
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/hpa.yaml
@@ -0,0 +1,31 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: "{{ .Release.Name }}-hpa"
+  namespace: {{ .Release.Namespace }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: "{{ .Release.Name }}-deployment-vllm-omni"
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/ingress.yaml b/examples/online_serving/chart-helm/templates/ingress.yaml
new file mode 100644
index 000000000..1749ec242
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/ingress.yaml
@@ -0,0 +1,32 @@
+{{- if .Values.ingress.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: "{{ .Release.Name }}-ingress"
+  namespace: {{ .Release.Namespace }}
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if .Values.ingress.ingressClassName }}
+  ingressClassName: {{ .Values.ingress.ingressClassName }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- toYaml .Values.ingress.tls | nindent 4 }}
+  {{- end }}
+  rules:
+    - host: {{ .Values.ingress.host }}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: "{{ include "chart.service-name" . }}"
+                port:
+                  number: {{ include "chart.service-port" . }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/poddisruptionbudget.yaml b/examples/online_serving/chart-helm/templates/poddisruptionbudget.yaml
new file mode 100644
index 000000000..b5d12502b
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/poddisruptionbudget.yaml
@@ -0,0 +1,12 @@
+{{- if gt (int .Values.replicaCount) 1 }}
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: "{{ .Release.Name }}-pdb"
+  namespace: {{ .Release.Namespace }}
+spec:
+  maxUnavailable: {{ default 1 .Values.maxUnavailablePodDisruptionBudget }}
+  selector:
+    matchLabels:
+    {{- include "chart.labels" . | nindent 6 }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/pvc.yaml b/examples/online_serving/chart-helm/templates/pvc.yaml
new file mode 100644
index 000000000..a433c10da
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/pvc.yaml
@@ -0,0 +1,16 @@
+{{- if .Values.modelCache.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: "{{ .Release.Name }}-model-cache"
+  namespace: {{ .Release.Namespace }}
+spec:
+  accessModes:
+    {{- toYaml .Values.modelCache.accessModes | nindent 4 }}
+  {{- if .Values.modelCache.storageClassName }}
+  storageClassName: {{ .Values.modelCache.storageClassName }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.modelCache.storageSize }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/secrets.yaml b/examples/online_serving/chart-helm/templates/secrets.yaml
new file mode 100644
index 000000000..4d94409f0
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/secrets.yaml
@@ -0,0 +1,23 @@
+{{- if .Values.secrets }}
+apiVersion: v1
+kind: Secret
+metadata:
+  name: "{{ .Release.Name }}-secrets"
+  namespace: {{ .Release.Namespace }}
+type: Opaque
+data:
+  {{- range $key, $val := .Values.secrets }}
+  {{ $key }}: {{ $val | b64enc | quote }}
+  {{- end }}
+---
+{{- end }}
+{{- if .Values.hfToken }}
+apiVersion: v1
+kind: Secret
+metadata:
+  name: "{{ .Release.Name }}-hf-token"
+  namespace: {{ .Release.Namespace }}
+type: Opaque
+data:
+  token: {{ .Values.hfToken | b64enc | quote }}
+{{- end }}
diff --git a/examples/online_serving/chart-helm/templates/service.yaml b/examples/online_serving/chart-helm/templates/service.yaml
new file mode 100644
index 000000000..ad243a3aa
--- /dev/null
+++ b/examples/online_serving/chart-helm/templates/service.yaml
@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: "{{ include "chart.service-name" . }}"
+  namespace: {{ .Release.Namespace }}
+spec:
+  type: ClusterIP
+  ports:
+    - name: {{ include "chart.service-port-name" . }}
+      port: {{ include "chart.service-port" . }}
+      targetPort: {{ include "chart.container-port-name" . }}
+      protocol: TCP
+  selector:
+  {{- include "chart.labels" . | nindent 4 }}
diff --git a/examples/online_serving/chart-helm/tests/deployment_test.yaml b/examples/online_serving/chart-helm/tests/deployment_test.yaml
new file mode 100644
index 000000000..e2c7b32c4
--- /dev/null
+++ b/examples/online_serving/chart-helm/tests/deployment_test.yaml
@@ -0,0 +1,181 @@
+suite: test deployment
+templates:
+  - deployment.yaml
+tests:
+  - it: should create deployment with default omni command
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Deployment
+      - equal:
+          path: spec.template.spec.containers[0].name
+          value: vllm-omni
+      - equal:
+          path: spec.template.spec.containers[0].command[0]
+          value: vllm
+      - equal:
+          path: spec.template.spec.containers[0].command[1]
+          value: serve
+      - equal:
+          path: spec.template.spec.containers[0].command[2]
+          value: Tongyi-MAI/Z-Image-Turbo
+      - equal:
+          path: spec.template.spec.containers[0].command[3]
+          value: "--omni"
+      - equal:
+          path: spec.template.spec.containers[0].command[4]
+          value: "--host"
+      - equal:
+          path: spec.template.spec.containers[0].command[5]
+          value: "0.0.0.0"
+      - equal:
+          path: spec.template.spec.containers[0].command[6]
+          value: "--port"
+      - equal:
+          path: spec.template.spec.containers[0].command[7]
+          value: "8000"
+
+  - it: should use custom model when set
+    set:
+      model: "Qwen/Qwen2.5-Omni-7B"
+    asserts:
+      - equal:
+          path: spec.template.spec.containers[0].command[2]
+          value: Qwen/Qwen2.5-Omni-7B
+
+  - it: should include omniArgs flags in command
+    set:
+      omniArgs:
+        vaeUseSlicing: true
+        vaeUseTiling: true
+        enableCpuOffload: true
+        numGpus: 2
+        cacheBackend: "tea_cache"
+        workerBackend: "ray"
+        extraArgs:
+          - "--enable-layerwise-offload"
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--vae-use-slicing"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--vae-use-tiling"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--enable-cpu-offload"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--num-gpus"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--cache-backend"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--worker-backend"
+      - contains:
+          path: spec.template.spec.containers[0].command
+          content: "--enable-layerwise-offload"
+
+  - it: should use full command override when image.command is set
+    set:
+      image:
+        command:
+          - "custom-binary"
+          - "--flag"
+    asserts:
+      - equal:
+          path: spec.template.spec.containers[0].command[0]
+          value: custom-binary
+      - equal:
+          path: spec.template.spec.containers[0].command[1]
+          value: "--flag"
+
+  - it: should mount shm and model-cache volumes
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].volumeMounts
+          content:
+            name: shm
+            mountPath: /dev/shm
+      - contains:
+          path: spec.template.spec.containers[0].volumeMounts
+          content:
+            name: model-cache
+            mountPath: /cache
+      - contains:
+          path: spec.template.spec.volumes
+          content:
+            name: shm
+            emptyDir:
+              medium: Memory
+              sizeLimit: 8Gi
+
+  - it: should use PVC for model-cache when modelCache is enabled
+    set:
+      modelCache:
+        enabled: true
+        storageSize: "50Gi"
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - contains:
+          path: spec.template.spec.volumes
+          content:
+            name: model-cache
+            persistentVolumeClaim:
+              claimName: RELEASE-NAME-model-cache
+
+  - it: should use emptyDir for model-cache when modelCache is disabled
+    set:
+      modelCache:
+        enabled: false
+        storageSize: "50Gi"
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - contains:
+          path: spec.template.spec.volumes
+          content:
+            name: model-cache
+            emptyDir: {}
+
+  - it: should set HF_HOME environment variable
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: HF_HOME
+            value: /cache/huggingface
+
+  - it: should set HF_TOKEN env when hfToken is provided
+    set:
+      hfToken: "hf_test_token_123"
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: HF_TOKEN
+            valueFrom:
+              secretKeyRef:
+                name: RELEASE-NAME-hf-token
+                key: token
+
+  - it: should create custom init containers when specified
+    set:
+      extraInit:
+        initContainers:
+          - name: my-init
+            image: busybox:latest
+            command: ["echo", "init"]
+    asserts:
+      - lengthEqual:
+          path: spec.template.spec.initContainers
+          count: 1
+      - equal:
+          path: spec.template.spec.initContainers[0].name
+          value: my-init
+      - equal:
+          path: spec.template.spec.initContainers[0].image
+          value: busybox:latest
diff --git a/examples/online_serving/chart-helm/tests/ingress_test.yaml b/examples/online_serving/chart-helm/tests/ingress_test.yaml
new file mode 100644
index 000000000..938cab824
--- /dev/null
+++ b/examples/online_serving/chart-helm/tests/ingress_test.yaml
@@ -0,0 +1,86 @@
+suite: test ingress
+templates:
+  - ingress.yaml
+tests:
+  - it: should not create Ingress when disabled
+    set:
+      ingress:
+        enabled: false
+    asserts:
+      - hasDocuments:
+          count: 0
+
+  - it: should create Ingress when enabled
+    set:
+      ingress:
+        enabled: true
+        host: "vllm-omni.example.com"
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - equal:
+          path: spec.rules[0].host
+          value: vllm-omni.example.com
+      - equal:
+          path: spec.rules[0].http.paths[0].path
+          value: /
+      - equal:
+          path: spec.rules[0].http.paths[0].pathType
+          value: Prefix
+      - equal:
+          path: spec.rules[0].http.paths[0].backend.service.name
+          value: RELEASE-NAME-service
+      - equal:
+          path: spec.rules[0].http.paths[0].backend.service.port.number
+          value: 80
+
+  - it: should set ingressClassName when specified
+    set:
+      ingress:
+        enabled: true
+        host: "vllm-omni.example.com"
+        ingressClassName: "nginx"
+    asserts:
+      - equal:
+          path: spec.ingressClassName
+          value: nginx
+
+  - it: should not set ingressClassName when empty
+    set:
+      ingress:
+        enabled: true
+        host: "vllm-omni.example.com"
+        ingressClassName: ""
+    asserts:
+      - notExists:
+          path: spec.ingressClassName
+
+  - it: should include annotations when specified
+    set:
+      ingress:
+        enabled: true
+        host: "vllm-omni.example.com"
+        annotations:
+          nginx.ingress.kubernetes.io/proxy-body-size: "100m"
+    asserts:
+      - isNotEmpty:
+          path: metadata.annotations
+
+  - it: should include TLS configuration when specified
+    set:
+      ingress:
+        enabled: true
+        host: "vllm-omni.example.com"
+        tls:
+          - secretName: vllm-omni-tls
+            hosts:
+              - vllm-omni.example.com
+    asserts:
+      - equal:
+          path: spec.tls[0].secretName
+          value: vllm-omni-tls
+      - equal:
+          path: spec.tls[0].hosts[0]
+          value: vllm-omni.example.com
diff --git a/examples/online_serving/chart-helm/tests/pvc_test.yaml b/examples/online_serving/chart-helm/tests/pvc_test.yaml
new file mode 100644
index 000000000..f27bed618
--- /dev/null
+++ b/examples/online_serving/chart-helm/tests/pvc_test.yaml
@@ -0,0 +1,73 @@
+suite: test pvc
+templates:
+  - pvc.yaml
+tests:
+  - it: should create PVC when modelCache is enabled
+    set:
+      modelCache:
+        enabled: true
+        storageSize: "50Gi"
+        storageClassName: ""
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: PersistentVolumeClaim
+      - equal:
+          path: spec.accessModes[0]
+          value: ReadWriteOnce
+      - equal:
+          path: spec.resources.requests.storage
+          value: 50Gi
+
+  - it: should not create PVC when modelCache is disabled
+    set:
+      modelCache:
+        enabled: false
+        storageSize: "50Gi"
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - hasDocuments:
+          count: 0
+
+  - it: should use custom storage size
+    set:
+      modelCache:
+        enabled: true
+        storageSize: "100Gi"
+        storageClassName: ""
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - equal:
+          path: spec.resources.requests.storage
+          value: 100Gi
+
+  - it: should set storageClassName when specified
+    set:
+      modelCache:
+        enabled: true
+        storageSize: "50Gi"
+        storageClassName: "fast-ssd"
+        accessModes:
+          - ReadWriteOnce
+    asserts:
+      - equal:
+          path: spec.storageClassName
+          value: fast-ssd
+
+  - it: should support ReadWriteMany access mode
+    set:
+      modelCache:
+        enabled: true
+        storageSize: "50Gi"
+        storageClassName: ""
+        accessModes:
+          - ReadWriteMany
+    asserts:
+      - equal:
+          path: spec.accessModes[0]
+          value: ReadWriteMany
diff --git a/examples/online_serving/chart-helm/tests/secrets_test.yaml b/examples/online_serving/chart-helm/tests/secrets_test.yaml
new file mode 100644
index 000000000..9de126039
--- /dev/null
+++ b/examples/online_serving/chart-helm/tests/secrets_test.yaml
@@ -0,0 +1,48 @@
+suite: test secrets
+templates:
+  - secrets.yaml
+tests:
+  - it: should create HF token secret when hfToken is provided
+    set:
+      hfToken: "hf_test_token_123"
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Secret
+      - equal:
+          path: metadata.name
+          value: RELEASE-NAME-hf-token
+      - exists:
+          path: data.token
+
+  - it: should not create any secrets when hfToken is empty and no secrets defined
+    set:
+      hfToken: ""
+      secrets: {}
+    asserts:
+      - hasDocuments:
+          count: 0
+
+  - it: should create both generic and HF token secrets
+    set:
+      hfToken: "hf_test_token_123"
+      secrets:
+        mykey: myvalue
+    asserts:
+      - hasDocuments:
+          count: 2
+
+  - it: should create only generic secrets when no hfToken
+    set:
+      hfToken: ""
+      secrets:
+        mykey: myvalue
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Secret
+      - equal:
+          path: metadata.name
+          value: RELEASE-NAME-secrets
diff --git a/examples/online_serving/chart-helm/values.yaml b/examples/online_serving/chart-helm/values.yaml
new file mode 100644
index 000000000..52c5bacbd
--- /dev/null
+++ b/examples/online_serving/chart-helm/values.yaml
@@ -0,0 +1,197 @@
+# -- Default values for chart vllm-omni
+# -- Declare variables to be passed into your templates.
+
+# -- HuggingFace model ID to serve
+model: "Tongyi-MAI/Z-Image-Turbo"
+
+# -- Image configuration
+image:
+  # -- Image repository
+  repository: "vllm/vllm-omni"
+  # -- Image tag
+  tag: "v0.16.0"
+  # -- Override the container command entirely. If empty, the chart constructs
+  # -- it automatically from model + omniArgs.
+  command: []
+  # -- Optional environment variables for the container
+  env: []
+  # -- Security context override
+  securityContext: {}
+
+# -- Container port
+containerPort: 8000
+# -- Service name (auto-generated from release name if empty)
+serviceName:
+# -- Service port
+servicePort: 80
+# -- Additional ports configuration
+extraPorts: []
+
+# -- Number of replicas
+replicaCount: 1
+
+# -- Deployment strategy configuration
+deploymentStrategy: {}
+
+# -- Resource configuration
+resources:
+  requests:
+    # -- Number of CPUs
+    cpu: 4
+    # -- CPU memory
+    memory: 24Gi
+    # -- Number of GPUs
+    nvidia.com/gpu: 1
+  limits:
+    # -- Number of CPUs
+    cpu: 4
+    # -- CPU memory
+    memory: 24Gi
+    # -- Number of GPUs
+    nvidia.com/gpu: 1
+
+# -- GPU model types for node affinity scheduling (optional)
+# -- Leave empty to schedule on any GPU node. Set to restrict to specific GPU types.
+# -- Example: ["NVIDIA-A100-SXM4-40GB"]
+gpuModels: []
+
+# -- vllm-omni specific CLI arguments
+omniArgs:
+  # -- Additional raw CLI flags appended to the serve command (list of strings)
+  extraArgs: []
+  # -- Enable VAE slicing for memory optimization
+  vaeUseSlicing: false
+  # -- Enable VAE tiling for memory optimization
+  vaeUseTiling: false
+  # -- Enable CPU offloading for diffusion models
+  enableCpuOffload: false
+  # -- Number of GPUs for diffusion inference (empty = auto)
+  numGpus:
+  # -- Path to stage configs file (empty = auto-detected from model)
+  stageConfigsPath:
+  # -- Cache backend: none, tea_cache, or cache_dit
+  cacheBackend: "none"
+  # -- Default sampling params as a JSON string
+  defaultSamplingParams:
+  # -- Worker backend: multi_process or ray
+  workerBackend: "multi_process"
+
+# -- HuggingFace token for gated models (optional)
+hfToken: ""
+
+# -- Shared memory size for PyTorch multiprocessing
+shmSize: "8Gi"
+
+# -- Model cache configuration (HuggingFace downloads)
+modelCache:
+  # -- Use a PersistentVolumeClaim for model cache (recommended for production)
+  enabled: true
+  # -- Storage size for the PVC
+  storageSize: "50Gi"
+  # -- Storage class name (empty = cluster default)
+  storageClassName: ""
+  # -- Access modes
+  accessModes:
+    - ReadWriteOnce
+
+# -- Autoscaling configuration
+autoscaling:
+  # -- Enable autoscaling
+  enabled: false
+  # -- Minimum replicas
+  minReplicas: 1
+  # -- Maximum replicas
+  maxReplicas: 10
+  # -- Target CPU utilization for autoscaling
+  targetCPUUtilizationPercentage: 80
+  # targetMemoryUtilizationPercentage: 80
+
+# -- ConfigMap data (key-value pairs injected as environment variables)
+configs: {}
+
+# -- Secrets data (key-value pairs, base64-encoded automatically)
+secrets: {}
+
+# -- External ConfigMaps/Secrets references
+externalConfigs: []
+
+# -- Custom Kubernetes objects
+customObjects: []
+
+# -- PodDisruptionBudget max unavailable
+maxUnavailablePodDisruptionBudget: ""
+
+# -- Additional init containers
+extraInit:
+  initContainers: []
+
+# -- Additional sidecar containers
+extraContainers: []
+
+# -- Startup probe configuration
+# -- Protects slow-starting containers. Liveness and readiness probes
+# -- do not start until the startup probe succeeds.
+# -- failureThreshold * periodSeconds = max startup time (40 * 30 = 1200s = 20 min)
+startupProbe:
+  # -- HTTP check configuration
+  httpGet:
+    # -- Path to check
+    path: /health
+    # -- Port to check (uses named port to stay in sync with containerPort)
+    port: "container-port"
+  # -- Failures before killing the container
+  failureThreshold: 40
+  # -- How often to perform the probe
+  periodSeconds: 30
+
+# -- Readiness probe configuration
+readinessProbe:
+  # -- How often to perform the probe
+  periodSeconds: 10
+  # -- Failures before marking unready
+  failureThreshold: 3
+  # -- HTTP check configuration
+  httpGet:
+    # -- Path to check
+    path: /health
+    # -- Port to check (uses named port to stay in sync with containerPort)
+    port: "container-port"
+
+# -- Liveness probe configuration
+livenessProbe:
+  # -- Failures before restarting
+  failureThreshold: 3
+  # -- How often to perform the probe
+  periodSeconds: 15
+  # -- HTTP check configuration
+  httpGet:
+    # -- Path to check
+    path: /health
+    # -- Port to check (uses named port to stay in sync with containerPort)
+    port: "container-port"
+
+# -- Ingress configuration
+ingress:
+  # -- Enable Ingress
+  enabled: false
+  # -- Ingress class name (e.g., nginx, traefik)
+  ingressClassName: ""
+  # -- Hostname for the Ingress rule
+  host: "vllm-omni.example.com"
+  # -- Additional annotations
+  annotations: {}
+  # -- TLS configuration
+  tls: []
+  #  - secretName: vllm-omni-tls
+  #    hosts:
+  #      - vllm-omni.example.com
+
+# -- Node selector for pod scheduling
+nodeSelector: {}
+
+# -- Tolerations for pod scheduling
+tolerations: []
+
+# -- Labels applied to all resources
+labels:
+  app: "vllm-omni"