chore(repo): init helm-charts repo with two charts and automated package/push

2025-11-17 16:50:28 +08:00
commit e8451c0675
28 changed files with 1905 additions and 0 deletions
--- a/.env.example
+++ b/.env.example
@ -0,0 +1,16 @@
+# Required: Helm OCI namespace to push to (host/org or host/user)
+# Examples: ghcr.io/your-org, gitea.example.com/your-user
+HELM_OCI_NAMESPACE=
+
+# Optional: Registry credentials (if not already logged in via `helm registry login`)
+HELM_USERNAME=
+HELM_PASSWORD=
+
+# Optional: Space separated chart dirs. If unset, script auto-discovers
+# CHART_DIRS="code-server-chart vllm-serve"
+
+# Optional: Set to 1 to only build locally without pushing
+# DRY_RUN=1
+
+# Optional: Extra flags for helm push
+# HELM_PUSH_EXTRA_ARGS="--insecure-skip-tls-verify"
--- a/.gitea/workflows/helm-publish.yml
+++ b/.gitea/workflows/helm-publish.yml
@ -0,0 +1,28 @@
+name: Helm Publish
+
+on:
+  push:
+    branches:
+      - "**"
+
+jobs:
+  package-and-push:
+    runs-on: ubuntu-latest
+    env:
+      HELM_OCI_NAMESPACE: ${{ secrets.HELM_OCI_NAMESPACE }}
+      HELM_USERNAME: ${{ secrets.HELM_USERNAME }}
+      HELM_PASSWORD: ${{ secrets.HELM_PASSWORD }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Helm
+        uses: azure/setup-helm@v4
+        with:
+          token: ${{ github.token }}
+          version: v3.12.3
+
+      - name: Package and Push Charts
+        run: |
+          set -euo pipefail
+          bash scripts/helm_publish.sh
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,11 @@
+# Helm artifacts
+*.tgz
+**/.packages/
+
+# Local env
+.env
+
+# OS/editor
+.DS_Store
+.idea/
+.vscode/
--- a/README.md
+++ b/README.md
@ -0,0 +1,47 @@
+# helm-charts repo
+
+This repository manages two Helm charts (e.g., `code-server-chart`, `vllm-serve`) and automates packaging and publishing on every `git push`.
+
+## How it works
+
+- Local pre-push hook runs `scripts/helm_publish.sh` to `helm package` and `helm push` all charts found under this folder (directories containing a `Chart.yaml`).
+- A Gitea Actions workflow at `.gitea/workflows/helm-publish.yml` does the same on the server side for each push.
+
+## Configure registry
+
+1. Copy `.env.example` to `.env` and fill in:
+
+```
+HELM_OCI_NAMESPACE=gitea.example.com/your-user
+HELM_USERNAME=your-username
+HELM_PASSWORD=your-token-or-password
+```
+
+2. For CI, add these as repository secrets in Gitea:
+   - `HELM_OCI_NAMESPACE`
+   - `HELM_USERNAME`
+   - `HELM_PASSWORD`
+
+The charts are pushed to `oci://$HELM_OCI_NAMESPACE` (Helm appends the chart name and version).
+
+## Chart discovery
+
+No configuration needed by default. The script auto-discovers chart directories by looking for `Chart.yaml` up to depth 2 (excluding nested `charts/` vendor dir).
+
+Optionally pin which chart directories to process:
+
+```
+export CHART_DIRS="code-server-chart vllm-serve"
+```
+
+## Run manually
+
+```
+./scripts/helm_publish.sh
+```
+
+Use `DRY_RUN=1` to only package locally:
+
+```
+DRY_RUN=1 ./scripts/helm_publish.sh
+```
--- a/code-server-chart/Chart.yaml
+++ b/code-server-chart/Chart.yaml
@ -0,0 +1,23 @@
+apiVersion: v2
+name: code-server
+description: A Helm chart for coder/code-server
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+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: 0.0.1
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+appVersion: 4.103.2
--- a/code-server-chart/README.md
+++ b/code-server-chart/README.md
@ -0,0 +1,2 @@
+# code-server-chart
+
--- a/code-server-chart/templates/NOTES.txt
+++ b/code-server-chart/templates/NOTES.txt
@ -0,0 +1,24 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ . }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "code-server.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "code-server.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "code-server.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl port-forward --namespace {{ .Release.Namespace }} service/{{ include "code-server.fullname" . }} 8080:http
+{{- end }}
+
+Administrator credentials:
+
+  Password: echo $(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "code-server.fullname" . }} -o jsonpath="{.data.password}" | base64 --decode)
--- a/code-server-chart/templates/_helpers.tpl
+++ b/code-server-chart/templates/_helpers.tpl
@ -0,0 +1,63 @@
+{{/* vim: set filetype=mustache: */}}
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "code-server.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "code-server.fullname" -}}
+{{- if .Values.fullnameOverride -}}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- if contains $name .Release.Name -}}
+{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "code-server.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Common labels
+*/}}
+{{- define "code-server.labels" -}}
+helm.sh/chart: {{ include "code-server.chart" . }}
+{{ include "code-server.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "code-server.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "code-server.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "code-server.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create -}}
+    {{ default (include "code-server.fullname" .) .Values.serviceAccount.name }}
+{{- else -}}
+    {{ default "default" .Values.serviceAccount.name }}
+{{- end -}}
+{{- end -}}
--- a/code-server-chart/templates/deployment.yaml
+++ b/code-server-chart/templates/deployment.yaml
@ -0,0 +1,190 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "code-server.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  replicas: {{ .Values.replicaCount | default 1 }}
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: {{ include "code-server.name" . }}
+      app.kubernetes.io/instance: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: {{ include "code-server.name" . }}
+        app.kubernetes.io/instance: {{ .Release.Name }}
+      {{- if .Values.podAnnotations }}
+      annotations: {{- toYaml .Values.podAnnotations | nindent 8 }}
+      {{- end }}
+    spec:
+      imagePullSecrets: {{- toYaml .Values.imagePullSecrets | nindent 8 }}
+      {{- if .Values.hostnameOverride }}
+      hostname: {{ .Values.hostnameOverride }}
+      {{- end }}
+      {{- if .Values.priorityClassName }}
+      priorityClassName: {{ .Values.priorityClassName }}
+      {{- end }}
+      {{- if .Values.securityContext.enabled }}
+      securityContext:
+        fsGroup: {{ .Values.securityContext.fsGroup }}
+      {{- end }}
+      {{- if or (and .Values.volumePermissions.enabled .Values.persistence.enabled) .Values.extraInitContainers }}
+      initContainers:
+      {{- if and .Values.volumePermissions.enabled .Values.persistence.enabled }}
+      - name: init-chmod-data
+        image: busybox:latest
+        imagePullPolicy: IfNotPresent
+        command:
+          - sh
+          - -c
+          - |
+            chown -R {{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.fsGroup }} /home/coder
+        securityContext:
+          runAsUser: {{ .Values.volumePermissions.securityContext.runAsUser }}
+        volumeMounts:
+        - name: data
+          mountPath: /home/coder
+      {{- end }}
+{{- if .Values.extraInitContainers }}
+{{ tpl .Values.extraInitContainers . | indent 6}}
+{{- end }}
+      {{- end }}
+      containers:
+{{- if .Values.extraContainers }}
+{{ tpl .Values.extraContainers . | indent 8}}
+{{- end }}
+        - name: {{ .Chart.Name }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          {{- if .Values.securityContext.enabled }}
+          securityContext:
+            runAsUser: {{ .Values.securityContext.runAsUser }}
+          {{- end }}
+          {{- if .Values.lifecycle.enabled }}
+          lifecycle:
+            {{- if .Values.lifecycle.postStart }}
+            postStart:
+              {{ toYaml .Values.lifecycle.postStart | nindent 14 }}
+            {{- end }}
+            {{- if .Values.lifecycle.preStop }}
+            preStop:
+              {{ toYaml .Values.lifecycle.preStop | nindent 14 }}
+            {{- end }}
+          {{- end }}
+          env:
+        {{- if .Values.extraVars }}
+{{ toYaml .Values.extraVars | indent 10 }}
+        {{- end }}
+          - name: PASSWORD
+            valueFrom:
+              secretKeyRef:
+              {{- if .Values.existingSecret }}
+                name: {{ .Values.existingSecret }}
+              {{- else }}
+                name: {{ template "code-server.fullname" . }}
+              {{- end }}
+                key: password
+        {{- if .Values.extraArgs }}
+          args:
+{{ toYaml .Values.extraArgs | indent 10 }}
+        {{- end }}
+          volumeMounts:
+          - name: data
+            mountPath: /home/coder
+          {{- range .Values.extraConfigmapMounts }}
+          - name: {{ .name }}
+            mountPath: {{ .mountPath }}
+            subPath: {{ .subPath | default "" }}
+            readOnly: {{ .readOnly }}
+          {{- end }}
+          {{- range .Values.extraSecretMounts }}
+          - name: {{ .name }}
+            mountPath: {{ .mountPath }}
+            subPath: {{ .subPath | default "" }}
+            readOnly: {{ .readOnly }}
+          {{- end }}
+          {{- range .Values.extraVolumeMounts }}
+          - name: {{ .name }}
+            mountPath: {{ .mountPath }}
+            subPath: {{ .subPath | default "" }}
+            readOnly: {{ .readOnly }}
+          {{- end }}
+          ports:
+            - name: http
+              containerPort: 8080
+              protocol: TCP
+          {{- range .Values.extraPorts }}
+            - name: {{ .name }}
+              containerPort: {{ .port }}
+              protocol: {{ .protocol }}
+          {{- end }}
+          livenessProbe:
+            httpGet:
+              path: /
+              port: http
+          readinessProbe:
+            httpGet:
+              path: /
+              port: http
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+        {{- tpl . $ | nindent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+      serviceAccountName: {{ template "code-server.serviceAccountName" . }}
+      volumes:
+      - name: data
+      {{- if .Values.persistence.enabled }}
+        {{- if not .Values.persistence.hostPath }}
+        persistentVolumeClaim:
+          claimName: {{ .Values.persistence.existingClaim | default (include "code-server.fullname" .) }}
+        {{- else }}
+        hostPath:
+          path: {{ .Values.persistence.hostPath }}
+          type: Directory
+        {{- end -}}
+      {{- else }}
+        emptyDir: {}
+      {{- end -}}
+      {{- range .Values.extraSecretMounts }}
+      - name: {{ .name }}
+        secret:
+          secretName: {{ .secretName }}
+          defaultMode: {{ .defaultMode }}
+      {{- end }}
+      {{- range .Values.extraConfigmapMounts }}
+      - name: {{ .name }}
+        configMap:
+          name: {{ .configMap }}
+          defaultMode: {{ .defaultMode }}
+      {{- end }}
+      {{- range .Values.extraVolumeMounts }}
+      - name: {{ .name }}
+        {{- if .existingClaim }}
+        persistentVolumeClaim:
+          claimName: {{ .existingClaim }}
+        {{- else if .hostPath }}
+        hostPath:
+          path: {{ .hostPath }}
+          type: Directory
+        {{- else }}
+        emptyDir:
+          {{- toYaml .emptyDir | nindent 10 }}
+        {{- end }}
+      {{- end }}
--- a/code-server-chart/templates/ingress.yaml
+++ b/code-server-chart/templates/ingress.yaml
@ -0,0 +1,63 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "code-server.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+{{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1beta1
+{{- else -}}
+apiVersion: extensions/v1beta1
+{{- end }}
+kind: Ingress
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "code-server.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:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+  {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion -}}
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ . }}
+            pathType: Prefix
+            backend:
+              service:
+                name: {{ $fullName }}
+                port: 
+                  number: {{ $svcPort }}
+          {{- end }}
+    {{- end }}
+  {{- else -}}
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ . }}
+            backend:
+              serviceName: {{ $fullName }}
+              servicePort: {{ $svcPort }}
+          {{- end }}
+    {{- end }}
+  {{- end }}
+{{- end }}
--- a/code-server-chart/templates/pvc.yaml
+++ b/code-server-chart/templates/pvc.yaml
@ -0,0 +1,29 @@
+{{- if and (and .Values.persistence.enabled (not .Values.persistence.existingClaim)) (not .Values.persistence.hostPath) }}
+kind: PersistentVolumeClaim
+apiVersion: v1
+metadata:
+  name: {{ include "code-server.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+{{- with .Values.persistence.annotations  }}
+  annotations:
+{{ toYaml . | indent 4 }}
+{{- end }}
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  accessModes:
+    - {{ .Values.persistence.accessMode | quote }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.size | quote }}
+{{- if .Values.persistence.storageClass }}
+{{- if (eq "-" .Values.persistence.storageClass) }}
+  storageClassName: ""
+{{- else }}
+  storageClassName: "{{ .Values.persistence.storageClass }}"
+{{- end }}
+{{- end }}
+{{- end }}
--- a/code-server-chart/templates/secrets.yaml
+++ b/code-server-chart/templates/secrets.yaml
@ -0,0 +1,20 @@
+{{- if not .Values.existingSecret }}
+apiVersion: v1
+kind: Secret
+metadata:
+  name: {{ include "code-server.fullname" . }}
+  annotations:
+    "helm.sh/hook": "pre-install"
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+type: Opaque
+data:
+  {{- if .Values.password }}
+  password: "{{ .Values.password | b64enc }}"
+  {{- else }}
+  password: "{{ randAlphaNum 24 | b64enc }}"
+  {{- end }}
+{{- end }}
--- a/code-server-chart/templates/service.yaml
+++ b/code-server-chart/templates/service.yaml
@ -0,0 +1,25 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "code-server.fullname" . }}
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  {{- range .Values.extraPorts }}
+    - port: {{ .port }}
+      targetPort: {{ .port }}
+      protocol: {{ .protocol }}
+      name: {{ .name }}
+  {{- end }}
+  selector:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
--- a/code-server-chart/templates/serviceaccount.yaml
+++ b/code-server-chart/templates/serviceaccount.yaml
@ -0,0 +1,11 @@
+{{- if or .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+  name: {{ template "code-server.serviceAccountName" . }}
+{{- end -}}
--- a/code-server-chart/templates/tests/test-connection.yaml
+++ b/code-server-chart/templates/tests/test-connection.yaml
@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "code-server.fullname" . }}-test-connection"
+  labels:
+    app.kubernetes.io/name: {{ include "code-server.name" . }}
+    helm.sh/chart: {{ include "code-server.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+  annotations:
+    "helm.sh/hook": test-success
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args:  ['{{ include "code-server.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never
--- a/code-server-chart/values.schema.json
+++ b/code-server-chart/values.schema.json
@ -0,0 +1,93 @@
+{
+  "type": "object",
+  "required": ["password"],
+  "properties": {
+    "image": {
+      "type": "object",
+      "description": "Container image configuration.",
+      "properties": {
+        "repository": {
+          "type": "string",
+          "description": "Container image repository.",
+          "default": "codercom/code-server",
+          "examples": ["codercom/code-server"]
+        },
+        "tag":{
+          "type": "string",
+          "description": "Container image tag.",
+          "default": "4.103.2"
+        }
+      }
+    },
+    "resources": {
+      "type": "object",
+      "description": "Container resource requests and limits, including CPU, Memory, and GPU.",
+      "properties": {
+        "limits": {
+          "type": "object",
+          "description": "Resource limits.",
+          "properties": {
+            "cpu": {
+              "type": "string"
+            },
+            "memory": {
+              "type": "string"
+            },
+            "nvidia.com/gpu": {
+              "type": "integer",
+              "description": "Number of NVIDIA GPUs (integer).",
+              "default": 0,
+              "minimum": 0
+            }
+          },
+          "additionalProperties": true
+        },
+        "requests": {
+          "type": "object",
+          "description": "Resource requests.",
+          "properties": {
+            "cpu": {
+              "type": "string"
+            },
+            "memory": {
+              "type": "string"
+            }
+          },
+          "additionalProperties": true
+        }
+      }
+    }, 
+    "password": {
+      "type": "string",
+      "description": "Password for the admin user.",
+      "examples": ["password"]
+    },
+    "persistence": {
+      "type": "object",
+      "description": "Persistent volume configuration.",
+      "properties": {
+        "storageClass": {
+          "type": "string",
+          "description": "Storage class name.",
+          "default": "standard",
+          "enum": ["nas-nfs","csi-cephfs-sc","sl-sc"],
+          "examples": ["nas-nfs","csi-cephfs-sc"]
+        },
+        "size": {
+          "type": "string",
+          "description": "Persistent volume size.",
+          "default": "10Gi",
+          "examples": ["10Gi","20Gi"]
+        },
+        "existingClaim": {
+          "type": "string",
+          "description": "Existing persistent volume claim name.",
+          "examples": ["pvc-12345678-1234-1234-1234-123456789012"]
+        }
+      }
+    }, 
+    "nodeSelector": {
+      "type": "object"
+    }
+  }
+}
--- a/code-server-chart/values.yaml
+++ b/code-server-chart/values.yaml
@ -0,0 +1,226 @@
+# Default values for code-server.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: codercom/code-server
+  tag: '4.103.2'
+  # repository: ghcr.io/kubeflow/kubeflow/notebook-servers/codeserver
+  # tag: "latest"
+  pullPolicy: IfNotPresent
+
+# Specifies one or more secrets to be used when pulling images from a
+# private container repository
+# https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry
+imagePullSecrets: []
+#  - name: registry-creds
+
+nameOverride: ""
+fullnameOverride: ""
+hostnameOverride: ""
+
+# The existing secret to use for code-server authentication in the frontend. the password is stored in the secret under the key `password`
+# existingSecret: ""
+password: ""
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+
+podAnnotations: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+priorityClassName: ""
+
+service:
+  type: LoadBalancer
+  port: 80
+
+ingress:
+  enabled: false
+  #annotations:
+  #  kubernetes.io/tls-acme: "true"
+  #hosts:
+  #  - host: code-server.example.loc
+  #    paths:
+  #      - /
+  ingressClassName: ""
+  #tls:
+  #  - secretName: code-server
+  #    hosts:
+  #      - code-server.example.loc
+
+# Optional additional arguments
+extraArgs: []
+  # These are the arguments normally passed to code-server; run
+  # code-server --help for a list of available options.
+  #
+  # Each argument and parameter must have its own entry; if you use
+  # --param value on the command line, then enter it here as:
+  #
+  # - --param
+  # - value
+  #
+  # If you receive an error like "Unknown option --param value", it may be
+  # because both the parameter and value are specified as a single argument,
+  # rather than two separate arguments (e.g. "- --param value" on a line).
+
+# Optional additional environment variables
+extraVars: []
+#  - name: DISABLE_TELEMETRY
+#    value: "true"
+# if dind is desired:
+#  - name: DOCKER_HOST
+#    value: "tcp://localhost:2376"
+
+##
+## Init containers parameters:
+## volumePermissions: Change the owner of the persist volume mountpoint to RunAsUser:fsGroup
+##
+volumePermissions:
+  enabled: false
+  securityContext:
+    runAsUser: 0
+
+## Pod Security Context
+## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/
+##
+securityContext:
+  enabled: true
+  fsGroup: 1000
+  runAsUser: 1000
+
+resources: 
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  limits:
+    cpu: 4000m
+    memory: 8192Mi
+    nvidia.com/gpu: "1"
+  requests:
+    cpu: 2000m
+    memory: 4000Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+## Persist data to a persistent volume
+persistence:
+  enabled: true
+  ## code-server data Persistent Volume Storage Class
+  ## If defined, storageClassName: <storageClass>
+  ## If set to "-", storageClassName: "", which disables dynamic provisioning
+  ## If undefined (the default) or set to null, no storageClassName spec is
+  ##   set, choosing the default provisioner.  (gp2 on AWS, standard on
+  ##   GKE, AWS & OpenStack)
+  ##
+  storageClass: "nas-nfs"
+  accessMode: ReadWriteOnce
+  size: 10Gi
+  annotations: {}
+  existingClaim: ""
+  # hostPath: /data
+
+lifecycle:
+  enabled: false
+  # postStart:
+  #  exec:
+  #    command:
+  #      - /bin/bash
+  #      - -c
+  #      - curl -s -L SOME_SCRIPT | bash
+
+  # for dind, the following may be helpful
+  # postStart:
+  #   exec:
+  #     command:
+  #       - /bin/sh
+  #       - -c
+  #       - |
+  #         sudo apt-get update \
+  #           && sudo apt-get install -y docker.io
+
+## Enable an Specify container in extraContainers.
+## This is meant to allow adding code-server dependencies, like docker-dind.
+extraContainers: |
+# If docker-dind is used, DOCKER_HOST env is mandatory to set in "extraVars"
+# - name: docker-dind
+#   image: docker:28.3.2-dind
+#   imagePullPolicy: IfNotPresent
+#   resources:
+#     requests:
+#       cpu: 1
+#       ephemeral-storage: "50Gi"
+#       memory: 10Gi
+#   securityContext:
+#     privileged: true
+#     procMount: Default
+#   env:
+#     - name: DOCKER_TLS_CERTDIR
+#       value: "" # disable TLS setup
+#   command:
+#     - dockerd
+#     - --host=unix:///var/run/docker.sock
+#     - --host=tcp://0.0.0.0:2376
+
+
+extraInitContainers: |
+# - name: customization
+#   image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+#   imagePullPolicy: IfNotPresent
+#   env:
+#     - name: SERVICE_URL
+#       value: https://open-vsx.org/vscode/gallery
+#     - name: ITEM_URL
+#       value: https://open-vsx.org/vscode/item
+#   command:
+#     - sh
+#     - -c
+#     - |
+#       code-server --install-extension ms-python.python
+#       code-server --install-extension golang.Go
+#   volumeMounts:
+#     - name: data
+#       mountPath: /home/coder
+
+## Additional code-server secret mounts
+extraSecretMounts: []
+  # - name: secret-files
+  #   mountPath: /etc/secrets
+  #   subPath: private.key # (optional)
+  #   secretName: code-server-secret-files
+  #   readOnly: true
+
+## Additional code-server volume mounts
+extraVolumeMounts: []
+  # - name: extra-volume
+  #   mountPath: /mnt/volume
+  #   readOnly: true
+  #   existingClaim: volume-claim
+  #   hostPath: ""
+  #   emptyDir: {}
+
+extraConfigmapMounts: []
+  # - name: certs-configmap
+  #   mountPath: /etc/code-server/ssl/
+  #   subPath: certificates.crt # (optional)
+  #   configMap: certs-configmap
+  #   readOnly: true
+
+extraPorts: []
+  # - name: minecraft
+  #   port: 25565
+  #   protocol: tcp
--- a/scripts/helm_publish.sh
+++ b/scripts/helm_publish.sh
@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Package and push all Helm charts found under the repo
+# Required env:
+#   HELM_OCI_NAMESPACE   e.g. ghcr.io/OWNER or gitea.example.com/OWNER
+# Optional env:
+#   HELM_USERNAME / HELM_PASSWORD for registry login
+#   CHART_DIRS: space-separated list of chart directories; if empty, auto-discover
+#   DRY_RUN=1: only package, do not push
+#   HELM_PUSH_EXTRA_ARGS: extra flags for `helm push` (e.g., --insecure-skip-tls-verify)
+
+ROOT_DIR="$(cd "$(dirname "$0")/.." && pwd)"
+cd "$ROOT_DIR"
+
+if [[ -z "${HELM_OCI_NAMESPACE:-}" ]]; then
+  echo "[helm_publish] HELM_OCI_NAMESPACE not set (e.g., ghcr.io/owner or gitea.example.com/owner)." >&2
+  exit 1
+fi
+
+# Derive registry host from HELM_OCI_NAMESPACE
+HELM_REGISTRY_HOST="${HELM_OCI_NAMESPACE%%/*}"
+
+# Auto-discover charts when CHART_DIRS not provided
+if [[ -z "${CHART_DIRS:-}" ]]; then
+  mapfile -t chart_paths < <(find . -maxdepth 2 -type f -name Chart.yaml -not -path "*/charts/*" | sort)
+  if [[ ${#chart_paths[@]} -eq 0 ]]; then
+    echo "[helm_publish] No charts found (no Chart.yaml)." >&2
+    exit 1
+  fi
+  CHART_DIRS=""
+  for p in "${chart_paths[@]}"; do
+    d="$(dirname "$p")"
+    CHART_DIRS+=" ${d#./}"
+  done
+fi
+
+# Login if credentials present
+if [[ -n "${HELM_USERNAME:-}" && -n "${HELM_PASSWORD:-}" ]]; then
+  echo "[helm_publish] Logging into registry ${HELM_REGISTRY_HOST} as ${HELM_USERNAME}"
+  helm registry login "$HELM_REGISTRY_HOST" -u "$HELM_USERNAME" -p "$HELM_PASSWORD"
+else
+  echo "[helm_publish] HELM_USERNAME/HELM_PASSWORD not set; assuming registry creds already configured"
+fi
+
+status=0
+for chart_dir in ${CHART_DIRS}; do
+  if [[ ! -f "$chart_dir/Chart.yaml" ]]; then
+    echo "[helm_publish] Skip $chart_dir (no Chart.yaml)"
+    continue
+  fi
+  echo "[helm_publish] Processing chart: $chart_dir"
+
+  # Ensure dependencies are built
+  if [[ -f "$chart_dir/Chart.yaml" ]]; then
+    helm dependency build "$chart_dir" || true
+  fi
+
+  pkg_out_dir="$chart_dir/.packages"
+  mkdir -p "$pkg_out_dir"
+
+  # Lint chart (non-fatal)
+  if ! helm lint "$chart_dir"; then
+    echo "[helm_publish] Warning: helm lint failed for $chart_dir"
+  fi
+
+  # Package chart
+  pkg_path=$(helm package "$chart_dir" --destination "$pkg_out_dir" | awk '{print $NF}')
+  if [[ ! -f "$pkg_path" ]]; then
+    echo "[helm_publish] Failed to package $chart_dir" >&2
+    status=1
+    continue
+  fi
+  echo "[helm_publish] Packaged: $pkg_path"
+
+  if [[ "${DRY_RUN:-}" == "1" ]]; then
+    echo "[helm_publish] DRY_RUN enabled; skip push for $pkg_path"
+    continue
+  fi
+
+  # Push to OCI registry; Helm will use chart name from the package
+  echo "[helm_publish] Pushing $pkg_path to oci://$HELM_OCI_NAMESPACE"
+  if ! helm push ${HELM_PUSH_EXTRA_ARGS:-} "$pkg_path" "oci://$HELM_OCI_NAMESPACE"; then
+    echo "[helm_publish] Push failed for $pkg_path" >&2
+    status=1
+  fi
+
+done
+
+exit $status
--- a/vllm-serve/.helmignore
+++ b/vllm-serve/.helmignore
@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/
--- a/vllm-serve/Chart.yaml
+++ b/vllm-serve/Chart.yaml
@ -0,0 +1,8 @@
+annotations:
+  helm.sh/resource-policy: keep
+apiVersion: v2
+appVersion: 1.16.0
+description: A Helm chart for deploying vLLM with NFS storage
+name: vllm-serve
+type: application
+version: 0.2.0
--- a/vllm-serve/templates/NOTES.txt
+++ b/vllm-serve/templates/NOTES.txt
@ -0,0 +1,16 @@
+1. Get the application URL by running these commands:
+{{- if contains "NodePort" .Values.svc.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "vllm-serve.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.svc.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "vllm-serve.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "vllm-serve.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.svc.port }}
+{{- else if contains "ClusterIP" .Values.svc.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "vllm-serve.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}
--- a/vllm-serve/templates/_helpers.tpl
+++ b/vllm-serve/templates/_helpers.tpl
@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "vllm-serve.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "vllm-serve.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "vllm-serve.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "vllm-serve.labels" -}}
+helm.sh/chart: {{ include "vllm-serve.chart" . }}
+{{ include "vllm-serve.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "vllm-serve.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "vllm-serve.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "vllm-serve.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "vllm-serve.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
--- a/vllm-serve/templates/lws.yaml
+++ b/vllm-serve/templates/lws.yaml
@ -0,0 +1,193 @@
+{{- if gt (int .Values.workerSize) 1 }}
+apiVersion: leaderworkerset.x-k8s.io/v1
+kind: LeaderWorkerSet
+metadata:
+  name: {{ .Release.Name }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  leaderWorkerTemplate:
+    size: {{ .Values.workerSize }}
+    restartPolicy: RecreateGroupOnPodRestart
+    leaderTemplate:
+      metadata:
+        labels:
+          role: leader
+      spec:
+        initContainers:
+        # 模型下载作为第一个 initContainer
+        - name: download-model
+          image: {{ .Values.model.download.image }}
+          imagePullPolicy: {{ .Values.imagePullPolicy | default "IfNotPresent" }}
+          env:
+            - name: HF_ENDPOINT
+              value: https://hf-mirror.com
+            - name: HUGGING_FACE_HUB_TOKEN
+              value: {{ .Values.model.huggingfaceToken }}
+          command:
+            - sh
+            - -c
+            - |
+              MODEL_NAME=$(basename "{{ .Values.model.huggingfaceName }}")
+              DEST_DIR="{{ .Values.model.localMountPath }}/Weight/$MODEL_NAME"
+              # DEST_DIR="{{ .Values.model.localMountPath }}/{{ .Values.model.huggingfaceName }}"
+              # 检查模型是否存在，不存在则下载
+              echo "DEST_DIR= $DEST_DIR"
+              if [ ! -f "$DEST_DIR/config.json" ]; then
+                ls -l {{ .Values.model.localMountPath }}
+                echo "Downloading model {{ .Values.model.huggingfaceName }} to $DEST_DIR"
+                wget https://hf-mirror.com/hfd/hfd.sh 
+                chmod a+x hfd.sh
+                apt update && apt upgrade
+                apt install aria2 -y
+                ./hfd.sh {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
+                # huggingface-cli download {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
+              else
+                echo "Model already exists at $DEST_DIR"
+              fi
+          volumeMounts:
+          - name: weight-volume
+            mountPath: {{ .Values.model.localMountPath }}
+        containers:
+          - name: vllm-leader
+            image: {{ .Values.vllm.image }}
+            imagePullPolicy:  IfNotPresent
+            securityContext:
+              capabilities:
+                add: [ "IPC_LOCK" ]
+            env:
+              # - name: HUGGING_FACE_HUB_TOKEN
+              #   value: {{ .Values.vllm.huggingfaceToken }}
+              - name: GLOO_SOCKET_IFNAME
+                value: eth0
+              - name: NCCL_SOCKET_IFNAME
+                value: eth0
+              - name: NCCL_IB_DISABLE
+                value: "0"
+              - name: NCCL_DEBUG
+                value: INFO
+              - name: NCCL_IB_HCA
+                value: mlx5_0:1
+              - name: NCCL_IB_GID_INDEX
+                value: "0" # 或 "7"，根据你的网络配置而定
+              - name: RAY_DEDUP_LOGS
+                value: "0"
+            command:
+              - sh
+              - -c
+              {{- if .Values.command }}
+              - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE); {{ .Values.command }}"
+              {{- else }}
+              - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE);
+                MODEL_NAME=$(basename '{{ .Values.model.huggingfaceName }}'); MODEL_PATH='{{ .Values.model.localMountPath }}/Weight/'$MODEL_NAME; 
+                python3 -m vllm.entrypoints.openai.api_server --port 8000 --model $MODEL_PATH --tensor-parallel-size {{ .Values.resources.gpuLimit }} --pipeline_parallel_size {{ .Values.workerSize }} --trust_remote_code"
+              {{- end }}
+            resources:
+              limits:
+                nvidia.com/gpu: "{{ .Values.resources.gpuLimit }}"
+                memory: {{ .Values.resources.memoryLimit }}
+                ephemeral-storage: 10Gi
+                rdma/rdma_shared_device_a: 10
+              requests:
+                ephemeral-storage: 10Gi
+                cpu: {{ .Values.resources.cpuRequest }}
+            ports:
+              - containerPort: 8000
+                name: http
+            readinessProbe:
+              tcpSocket:
+                #httpGet:
+                #path: /health
+                port: 8000
+              initialDelaySeconds: 120
+              periodSeconds: 20
+              timeoutSeconds: 5
+            volumeMounts:
+              - mountPath: /dev/shm
+                name: dshm
+              - name: weight-volume
+                mountPath:  {{ .Values.model.localMountPath }}
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: {{ .Values.resources.shmSize }}
+        - name: weight-volume
+          persistentVolumeClaim:
+            claimName: {{ .Release.Name }}-pvc-model 
+        {{- with .Values.nodeSelector }}
+        nodeSelector:
+          {{- toYaml . | nindent 10 }}
+        {{- end }}
+        {{- with .Values.affinity }}
+        affinity:
+          {{- toYaml . | nindent 10 }}
+        {{- end }}
+        {{- with .Values.tolerations }}
+        tolerations:
+          {{- toYaml . | nindent 10 }}
+        {{- end }}
+    workerTemplate:
+      spec:
+        containers:
+          - name: vllm-worker
+            image: {{ .Values.vllm.image }}
+            imagePullPolicy:  IfNotPresent
+            securityContext:
+              capabilities:
+                add: [ "IPC_LOCK" ]
+            command:
+              - sh
+              - -c
+              - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh worker --ray_address=$(LWS_LEADER_ADDRESS)"
+            resources:
+              limits:
+                nvidia.com/gpu: "{{ .Values.resources.gpuLimit }}"
+                memory: {{ .Values.resources.memoryLimit }}
+                ephemeral-storage: 10Gi
+                rdma/rdma_shared_device_a: 10
+              requests:
+                ephemeral-storage: 10Gi
+                cpu: {{ .Values.resources.cpuRequest }}
+            env:
+              # - name: HUGGING_FACE_HUB_TOKEN
+              #   value: {{ .Values.vllm.huggingfaceToken }}
+              - name: GLOO_SOCKET_IFNAME
+                value: eth0
+              - name: NCCL_SOCKET_IFNAME
+                value: eth0
+              - name: NCCL_IB_DISABLE
+                value: "0"
+              - name: NCCL_DEBUG
+                value: INFO
+              - name: NCCL_IB_HCA
+                value: mlx5_0:1
+              - name: NCCL_IB_GID_INDEX
+                value: "0" # 或 "7"，根据你的网络配置而定
+              - name: RAY_DEDUP_LOGS
+                value: "0"
+            volumeMounts:
+              - mountPath: /dev/shm
+                name: dshm
+              - name: weight-volume
+                mountPath: {{ .Values.model.localMountPath }}
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: {{ .Values.resources.shmSize }}
+        - name: weight-volume
+          persistentVolumeClaim:
+            claimName: {{ .Release.Name }}-pvc-model
+        {{- with .Values.nodeSelector }}
+        nodeSelector:
+          {{- toYaml . | nindent 10 }}
+        {{- end }}
+        {{- with .Values.affinity }}
+        affinity:
+          {{- toYaml . | nindent 10 }}
+        {{- end }}
+        {{- with .Values.tolerations }}
+        tolerations:
+          {{- toYaml . | nindent 10 }}
+        {{- end }} 
+{{- end }}
--- a/vllm-serve/templates/nfs-pvc.yaml
+++ b/vllm-serve/templates/nfs-pvc.yaml
@ -0,0 +1,40 @@
+#apiVersion: v1
+#kind: PersistentVolume
+#metadata:
+#  name: {{ .Release.Name }}-pv-model
+#spec:
+#  storageClassName: weight # {{ .Values.nfs.storageClass | default "local-path" }}
+#  capacity:
+#    storage: {{ .Values.nfs.pvSize }}
+#  accessModes:
+#    - ReadWriteMany
+#  persistentVolumeReclaimPolicy: Retain
+#  #  nfs:
+#  #    path: {{ .Values.nfs.path }}
+#  #    server: {{ .Values.nfs.server }}
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ .Release.Name }}-pvc-model
+  # annotations:
+spec:
+  accessModes:
+    - ReadWriteMany
+  resources:
+    requests:
+      storage: {{ .Values.nfs.pvcSize }}
+  # volumeName: {{ .Release.Name }}-pv-model 
+  storageClassName: weight 
+
+#apiVersion: v1
+#kind: PersistentVolumeClaim
+#metadata:
+#  name: {{ .Release.Name }}-pvc-model
+#spec:
+#  accessModes:
+#    - ReadWriteMany
+#  resources:
+#    requests:
+#      storage: 20Gi
+#  storageClassName: nas-dataset
--- a/vllm-serve/templates/services.yaml
+++ b/vllm-serve/templates/services.yaml
@ -0,0 +1,35 @@
+#apiVersion: v1
+#kind: Service
+#metadata:
+#  name: infer-leader-loadbalancer
+#spec:
+#  type: LoadBalancer
+#  selector:
+#    leaderworkerset.sigs.k8s.io/name: infer
+#    role: leader
+#  ports:
+#    - protocol: TCP
+#      port: 8080
+#      targetPort: 8080
+#
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ .Release.Name }}-svc
+spec:
+  type: {{ .Values.svc.type | default "LoadBalancer" }}
+  {{- if gt (int .Values.workerSize) 1 }}
+  selector:
+    leaderworkerset.sigs.k8s.io/name: {{ .Release.Name }} 
+    role: leader
+  {{- else }}
+  selector:
+    app: {{ .Release.Name }}
+  {{- end }}
+  ports:
+    - protocol: TCP
+      port: {{ .Values.svc.port | default 80 }}
+      targetPort: http # {{ .Values.svc.targetPort | default 8080 }}
+      # nodePort: {{ .Values.svc.nodePort | default 30080 }}
+
--- a/vllm-serve/templates/single.yaml
+++ b/vllm-serve/templates/single.yaml
@ -0,0 +1,127 @@
+{{- if eq (int .Values.workerSize) 1 }}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ .Release.Name }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      app:  {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app: {{ .Release.Name }}
+    spec:
+      initContainers:
+     # 模型下载作为第一个 initContainer
+      - name: download-model
+        image: {{ .Values.model.download.image }}
+        imagePullPolicy: IfNotPresent
+        env:
+          - name: HF_ENDPOINT
+            value: https://hf-mirror.com
+          - name: HUGGING_FACE_HUB_TOKEN
+            value: {{ .Values.model.huggingfaceToken }}
+        command:
+          - sh
+          - -c
+          - |
+            MODEL_NAME=$(basename "{{ .Values.model.huggingfaceName }}")
+            DEST_DIR="{{ .Values.model.localMountPath }}/Weight/$MODEL_NAME"
+            # DEST_DIR="{{ .Values.model.localMountPath }}/{{ .Values.model.huggingfaceName }}"
+            # 检查模型是否存在，不存在则下载
+            echo "DEST_DIR= $DEST_DIR"
+            if [ ! -f "$DEST_DIR/config.json" ]; then
+              ls -l {{ .Values.model.localMountPath }}
+              echo "Downloading model {{ .Values.model.huggingfaceName }} to $DEST_DIR"
+              wget https://hf-mirror.com/hfd/hfd.sh 
+              chmod a+x hfd.sh
+              apt update && apt upgrade
+              apt install aria2 -y
+              ./hfd.sh {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
+              # huggingface-cli download {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
+            else
+              echo "Model already exists at $DEST_DIR"
+            fi
+        volumeMounts:
+        - name: weight-volume
+          mountPath: {{ .Values.model.localMountPath }}
+      containers:
+      - name: vllm-pod
+        image: {{ .Values.vllm.image }}
+        imagePullPolicy:  IfNotPresent
+        env:
+        - name: HUGGING_FACE_HUB_TOKEN
+          value: {{ .Values.vllm.huggingfaceToken }}
+        - name: RAY_DEDUP_LOGS
+          value: "0"
+        command:
+          - sh
+          - -c
+          {{- if .Values.command }}
+          - {{ .Values.command | quote }}
+          {{- else }}
+          - |
+            MODEL_NAME=$(basename '{{ .Values.model.huggingfaceName }}');
+            MODEL_PATH='{{ .Values.model.localMountPath }}/Weight/'$MODEL_NAME;
+            python3 -m vllm.entrypoints.openai.api_server \
+              --port 8000 \
+              --model $MODEL_PATH \
+              --tensor-parallel-size {{ .Values.resources.gpuLimit }} \
+              --pipeline_parallel_size {{ .Values.workerSize }} \
+              --trust_remote_code
+          {{- end }}
+          # - "
+          #   MODEL_NAME=$(basename '{{ .Values.model.huggingfaceName }}'); 
+          #   MODEL_PATH='{{ .Values.model.localMountPath }}/Weight/'$MODEL_NAME; 
+          #   python3 -m vllm.entrypoints.openai.api_server --port 8080 --model $MODEL_PATH --tensor-parallel-size {{ .Values.resources.gpuLimit }} --pipeline_parallel_size {{ .Values.workerSize }} --trust_remote_code" 
+        resources:
+          limits:
+            nvidia.com/gpu: "{{ .Values.resources.gpuLimit }}"
+            memory: {{ .Values.resources.memoryLimit }}
+            ephemeral-storage: 10Gi
+          requests:
+            ephemeral-storage: 10Gi
+            cpu: {{ .Values.resources.cpuRequest }}
+        ports:
+        - containerPort: 8000
+          name: http
+        readinessProbe:
+          #tcpSocket:
+          httpGet:
+            path: /health
+            port: 8000
+          initialDelaySeconds: 120
+          periodSeconds: 20
+          timeoutSeconds: 5
+        volumeMounts:
+          - mountPath: /dev/shm
+            name: dshm
+          - name: weight-volume
+            mountPath:  {{ .Values.model.localMountPath }}
+      volumes:
+      - name: dshm
+        emptyDir:
+          medium: Memory
+          sizeLimit: {{ .Values.resources.shmSize }}
+      - name: weight-volume
+        persistentVolumeClaim:
+          claimName: {{ .Release.Name }}-pvc-model
+      # - name: weight-volume
+      #   nfs:
+      #     path: "/volume1/Dataset/PVStore/lab-data-model-pvc-c0beeab1-6dd5-4c6a-bd2c-6ce9e114c25e/Weight"
+      #     server: "10.6.80.11"        
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+{{- end }}
--- a/vllm-serve/values.schema.json
+++ b/vllm-serve/values.schema.json
@ -0,0 +1,346 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "vllm-serve Helm Chart Values",
+  "description": "Schema for vllm-serve Helm chart values",
+  "type": "object",
+  "properties": {
+    "model": {
+      "type": "object",
+      "description": "模型配置",
+      "properties": {
+        "huggingfaceName": {
+          "type": "string",
+          "description": "HuggingFace 模型名称",
+          "default": "Qwen/Qwen2.5-0.5B-Instruct",
+          "enum": [
+            "swiss-ai/Apertus-8B-2509",
+            "swiss-ai/Apertus-70B-Instruct-2509",
+            "BAAI/Aquila-7B",
+            "BAAI/AquilaChat-7B",
+            "arcee-ai/AFM-4.5B-Base",
+            "Snowflake/snowflake-arctic-base",
+            "Snowflake/snowflake-arctic-instruct",
+            "baichuan-inc/Baichuan2-13B-Chat",
+            "baichuan-inc/Baichuan-7B",
+            "inclusionAI/Ling-lite-1.5",
+            "inclusionAI/Ling-plus",
+            "inclusionAI/Ling-mini-2.0",
+            "ibm-ai-platform/Bamba-9B-fp8",
+            "ibm-ai-platform/Bamba-9B",
+            "bigscience/bloom",
+            "bigscience/bloomz",
+            "zai-org/chatglm2-6b",
+            "zai-org/chatglm3-6b",
+            "CohereLabs/c4ai-command-r-v01",
+            "CohereLabs/c4ai-command-r7b-12-2024",
+            "CohereLabs/c4ai-command-a-03-2025",
+            "CohereLabs/command-a-reasoning-08-2025",
+            "databricks/dbrx-base",
+            "databricks/dbrx-instruct",
+            "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
+            "deepseek-ai/deepseek-llm-67b-base",
+            "deepseek-ai/deepseek-llm-7b-chat",
+            "deepseek-ai/DeepSeek-V2",
+            "deepseek-ai/DeepSeek-V2-Chat",
+            "deepseek-ai/DeepSeek-V3",
+            "deepseek-ai/DeepSeek-R1",
+            "deepseek-ai/DeepSeek-V3.1",
+            "rednote-hilab/dots.llm1.base",
+            "rednote-hilab/dots.llm1.inst",
+            "rednote-hilab/dots.ocr",
+            "baidu/ERNIE-4.5-0.3B-PT",
+            "baidu/ERNIE-4.5-21B-A3B-PT",
+            "baidu/ERNIE-4.5-300B-A47B-PT",
+            "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct",
+            "LGAI-EXAONE/EXAONE-4.0-32B",
+            "mgleize/fairseq2-dummy-Llama-3.2-1B",
+            "tiiuae/falcon-7b",
+            "tiiuae/falcon-40b",
+            "tiiuae/falcon-rw-7b",
+            "tiiuae/falcon-mamba-7b",
+            "tiiuae/falcon-mamba-7b-instruct",
+            "tiiuae/Falcon-H1-34B-Base",
+            "tiiuae/Falcon-H1-34B-Instruct",
+            "allenai/FlexOlmo-7x7B-1T",
+            "allenai/FlexOlmo-7x7B-1T-RT",
+            "google/gemma-2b",
+            "google/gemma-1.1-2b-it",
+            "google/gemma-2-9b",
+            "google/gemma-2-27b",
+            "google/gemma-3-1b-it",
+            "google/gemma-3n-E2B-it",
+            "google/gemma-3n-E4B-it",
+            "zai-org/glm-4-9b-chat-hf",
+            "zai-org/GLM-4-32B-0414",
+            "zai-org/GLM-4.5",
+            "gpt2",
+            "gpt2-xl",
+            "bigcode/starcoder",
+            "bigcode/gpt_bigcode-santacoder",
+            "WizardLM/WizardCoder-15B-V1.0",
+            "EleutherAI/gpt-j-6b",
+            "nomic-ai/gpt4all-j",
+            "EleutherAI/gpt-neox-20b",
+            "EleutherAI/pythia-12b",
+            "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
+            "databricks/dolly-v2-12b",
+            "stabilityai/stablelm-tuned-alpha-7b",
+            "openai/gpt-oss-120b",
+            "openai/gpt-oss-20b",
+            "ibm-granite/granite-3.0-2b-base",
+            "ibm-granite/granite-3.1-8b-instruct",
+            "ibm/PowerLM-3b",
+            "ibm-granite/granite-3.0-1b-a400m-base",
+            "ibm-granite/granite-3.0-3b-a800m-instruct",
+            "ibm/PowerMoE-3b",
+            "ibm-granite/granite-4.0-tiny-preview",
+            "parasail-ai/GritLM-7B-vllm",
+            "hpcai-tech/grok-1",
+            "tencent/Hunyuan-7B-Instruct",
+            "tencent/Hunyuan-A13B-Instruct",
+            "tencent/Hunyuan-A13B-Pretrain",
+            "tencent/Hunyuan-A13B-Instruct-FP8",
+            "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B",
+            "internlm/internlm-7b",
+            "internlm/internlm-chat-7b",
+            "internlm/internlm2-7b",
+            "internlm/internlm2-chat-7b",
+            "internlm/internlm3-8b-instruct",
+            "inceptionai/jais-13b",
+            "inceptionai/jais-13b-chat",
+            "inceptionai/jais-30b-v3",
+            "inceptionai/jais-30b-chat-v3",
+            "ai21labs/AI21-Jamba-1.5-Large",
+            "ai21labs/AI21-Jamba-1.5-Mini",
+            "ai21labs/Jamba-v0.1",
+            "LiquidAI/LFM2-1.2B",
+            "LiquidAI/LFM2-700M",
+            "LiquidAI/LFM2-350M",
+            "LiquidAI/LFM2-8B-A1B-preview",
+            "meta-llama/Meta-Llama-3.1-405B-Instruct",
+            "meta-llama/Meta-Llama-3.1-70B",
+            "meta-llama/Meta-Llama-3-70B-Instruct",
+            "meta-llama/Llama-2-70b-hf",
+            "01-ai/Yi-34B",
+            "state-spaces/mamba-130m-hf",
+            "state-spaces/mamba-790m-hf",
+            "state-spaces/mamba-2.8b-hf",
+            "mistralai/Mamba-Codestral-7B-v0.1",
+            "XiaomiMiMo/MiMo-7B-RL",
+            "openbmb/MiniCPM-2B-sft-bf16",
+            "openbmb/MiniCPM-2B-dpo-bf16",
+            "openbmb/MiniCPM-S-1B-sft",
+            "openbmb/MiniCPM3-4B",
+            "MiniMaxAI/MiniMax-M2",
+            "mistralai/Mistral-7B-v0.1",
+            "mistralai/Mistral-7B-Instruct-v0.1",
+            "mistralai/Mixtral-8x7B-v0.1",
+            "mistralai/Mixtral-8x7B-Instruct-v0.1",
+            "mistral-community/Mixtral-8x22B-v0.1",
+            "mosaicml/mpt-7b",
+            "mosaicml/mpt-7b-storywriter",
+            "mosaicml/mpt-30b",
+            "nvidia/Minitron-8B-Base",
+            "mgoin/Nemotron-4-340B-Base-hf-FP8",
+            "nvidia/Nemotron-H-8B-Base-8K",
+            "nvidia/Nemotron-H-47B-Base-8K",
+            "nvidia/Nemotron-H-56B-Base-8K",
+            "allenai/OLMo-1B-hf",
+            "allenai/OLMo-7B-hf",
+            "allenai/OLMo-2-0425-1B",
+            "allenai/OLMoE-1B-7B-0924",
+            "allenai/OLMoE-1B-7B-0924-Instruct",
+            "facebook/opt-66b",
+            "facebook/opt-iml-max-30b",
+            "OrionStarAI/Orion-14B-Base",
+            "OrionStarAI/Orion-14B-Chat",
+            "microsoft/phi-1_5",
+            "microsoft/phi-2",
+            "microsoft/Phi-4-mini-instruct",
+            "microsoft/Phi-4",
+            "microsoft/Phi-3-mini-4k-instruct",
+            "microsoft/Phi-3-mini-128k-instruct",
+            "microsoft/Phi-3-medium-128k-instruct",
+            "microsoft/Phi-3.5-MoE-instruct",
+            "adept/persimmon-8b-base",
+            "adept/persimmon-8b-chat",
+            "pfnet/plamo-2-1b",
+            "pfnet/plamo-2-8b",
+            "Qwen/Qwen-7B",
+            "Qwen/Qwen-7B-Chat",
+            "Qwen/QwQ-32B-Preview",
+            "Qwen/Qwen2-7B-Instruct",
+            "Qwen/Qwen2-7B",
+            "Qwen/Qwen2.5-0.5B-Instruct",
+            "Qwen/Qwen1.5-MoE-A2.7B",
+            "Qwen/Qwen1.5-MoE-A2.7B-Chat",
+            "Qwen/Qwen3-8B",
+            "Qwen/Qwen3-30B-A3B",
+            "Qwen/Qwen3-Next-80B-A3B-Instruct",
+            "ByteDance-Seed/Seed-OSS-36B-Instruct",
+            "stabilityai/stablelm-3b-4e1t",
+            "stabilityai/stablelm-base-alpha-7b-v2",
+            "bigcode/starcoder2-3b",
+            "bigcode/starcoder2-7b",
+            "bigcode/starcoder2-15b",
+            "upstage/solar-pro-preview-instruct",
+            "Tele-AI/TeleChat2-3B",
+            "Tele-AI/TeleChat2-7B",
+            "Tele-AI/TeleChat2-35B",
+            "CofeAI/FLM-2-52B-Instruct-2407",
+            "CofeAI/Tele-FLM",
+            "xverse/XVERSE-7B-Chat",
+            "xverse/XVERSE-13B-Chat",
+            "xverse/XVERSE-65B-Chat",
+            "MiniMaxAI/MiniMax-M1-40k",
+            "MiniMaxAI/MiniMax-M1-80k",
+            "MiniMaxAI/MiniMax-Text-01",
+            "Zyphra/Zamba2-7B-instruct",
+            "Zyphra/Zamba2-2.7B-instruct",
+            "Zyphra/Zamba2-1.2B-instruct",
+            "meituan-longcat/LongCat-Flash-Chat",
+            "meituan-longcat/LongCat-Flash-Chat-FP8",
+            "rhymes-ai/Aria",
+            "CohereForAI/aya-vision-8b",
+            "CohereForAI/aya-vision-32b",
+            "Open-Bee/Bee-8B-RL",
+            "Open-Bee/Bee-8B-SFT",
+            "Salesforce/blip2-opt-2.7b",
+            "Salesforce/blip2-opt-6.7b",
+            "facebook/chameleon-7b",
+            "CohereLabs/command-a-vision-07-2025",
+            "deepseek-ai/deepseek-vl2-tiny",
+            "deepseek-ai/deepseek-vl2-small",
+            "deepseek-ai/deepseek-vl2",
+            "deepseek-ai/DeepSeek-OCR",
+            "baidu/ERNIE-4.5-VL-28B-A3B-PT",
+            "baidu/ERNIE-4.5-VL-424B-A47B-PT",
+            "adept/fuyu-8b",
+            "google/gemma-3-4b-it",
+            "google/gemma-3-27b-it",
+            "zai-org/glm-4v-9b",
+            "zai-org/cogagent-9b-20241220",
+            "zai-org/GLM-4.1V-9B-Thinking",
+            "zai-org/GLM-4.5V",
+            "ibm-granite/granite-speech-3.3-8b",
+            "h2oai/h2ovl-mississippi-800m",
+            "h2oai/h2ovl-mississippi-2b",
+            "HuggingFaceM4/Idefics3-8B-Llama3",
+            "internlm/Intern-S1",
+            "internlm/Intern-S1-mini",
+            "OpenGVLab/InternVL3_5-14B",
+            "OpenGVLab/InternVL3-9B",
+            "OpenGVLab/InternVideo2_5_Chat_8B",
+            "OpenGVLab/InternVL2_5-4B",
+            "OpenGVLab/Mono-InternVL-2B",
+            "OpenGVLab/InternVL2-4B",
+            "OpenGVLab/InternVL3-1B-hf",
+            "Kwai-Keye/Keye-VL-8B-Preview",
+            "Kwai-Keye/Keye-VL-1_5-8B",
+            "moonshotai/Kimi-VL-A3B-Instruct",
+            "moonshotai/Kimi-VL-A3B-Thinking",
+            "lightonai/LightOnOCR-1B",
+            "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+            "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+            "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+            "nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1",
+            "llava-hf/llava-1.5-7b-hf",
+            "TIGER-Lab/Mantis-8B-siglip-llama3",
+            "mistral-community/pixtral-12b",
+            "llava-hf/llava-v1.6-mistral-7b-hf",
+            "llava-hf/llava-v1.6-vicuna-7b-hf",
+            "llava-hf/LLaVA-NeXT-Video-7B-hf",
+            "llava-hf/llava-onevision-qwen2-7b-ov-hf",
+            "llava-hf/llava-onevision-qwen2-0.5b-ov-hf",
+            "mispeech/midashenglm-7b",
+            "openbmb/MiniCPM-o-2_6",
+            "openbmb/MiniCPM-V-2",
+            "openbmb/MiniCPM-Llama3-V-2_5",
+            "openbmb/MiniCPM-V-2_6",
+            "openbmb/MiniCPM-V-4",
+            "openbmb/MiniCPM-V-4_5",
+            "MiniMaxAI/MiniMax-VL-01",
+            "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+            "allenai/Molmo-7B-D-0924",
+            "allenai/Molmo-7B-O-0924",
+            "nvidia/NVLM-D-72B",
+            "AIDC-AI/Ovis2-1B",
+            "AIDC-AI/Ovis1.6-Llama3.2-3B",
+            "AIDC-AI/Ovis2.5-9B",
+            "google/paligemma-3b-pt-224",
+            "google/paligemma-3b-mix-224",
+            "google/paligemma2-3b-ft-docci-448",
+            "microsoft/Phi-3-vision-128k-instruct",
+            "microsoft/Phi-3.5-vision-instruct",
+            "microsoft/Phi-4-multimodal-instruct",
+            "mistralai/Pixtral-12B-2409",
+            "Qwen/Qwen-VL",
+            "Qwen/Qwen-VL-Chat",
+            "Qwen/Qwen2-Audio-7B-Instruct",
+            "Qwen/QVQ-72B-Preview",
+            "Qwen/Qwen2-VL-7B-Instruct",
+            "Qwen/Qwen2-VL-72B-Instruct",
+            "Qwen/Qwen2.5-VL-3B-Instruct",
+            "Qwen/Qwen2.5-VL-72B-Instruct",
+            "Qwen/Qwen2.5-Omni-3B",
+            "Qwen/Qwen2.5-Omni-7B",
+            "Qwen/Qwen3-VL-4B-Instruct",
+            "Qwen/Qwen3-VL-30B-A3B-Instruct",
+            "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+            "Qwen/Qwen3-Omni-30B-A3B-Thinking",
+            "YannQi/R-4B",
+            "Skywork/Skywork-R1V-38B",
+            "SmolVLM2-2.2B-Instruct",
+            "stepfun-ai/step3",
+            "omni-search/Tarsier-7b",
+            "omni-search/Tarsier-34b",
+            "omni-research/Tarsier2-Recap-7b",
+            "omni-research/Tarsier2-7b-0115"
+          ]
+        }
+      },
+      "required": ["huggingfaceName"]
+    },
+    "resources": {
+      "type": "object",
+      "description": "资源配置",
+      "properties": {
+        "gpuLimit": {
+          "type": "integer",
+          "description": "GPU 限制",
+          "default": 1,
+          "minimum": 1
+        },
+        "cpuRequest": {
+          "type": "integer",
+          "description": "CPU 请求",
+          "default": 12,
+          "minimum": 1
+        },
+        "memoryLimit": {
+          "type": "string",
+          "description": "内存限制",
+          "default": "16Gi",
+          "pattern": "^[0-9]+(\\.[0-9]+)?(Mi|Gi|Ti)$"
+        },
+        "shmSize": {
+          "type": "string",
+          "description": "共享内存大小",
+          "default": "20Gi",
+          "pattern": "^[0-9]+(\\.[0-9]+)?(Mi|Gi|Ti)$"
+        }
+      }
+    },
+    "workerSize": {
+      "type": "integer",
+      "description": "Worker 数量",
+      "default": 1,
+      "minimum": 1
+    },
+    "command": {
+      "type": "string",
+      "description": "自定义命令，模型路径路为 /Model/Weight/Qwen3-0.6B, LoRA 路径为 /Model/LoRA/Qwen3-0.6B (可选)  \n e.g. vllm serve --model /Model/Weight/Qwen3-0.6B ",
+      "default": ""
+    }
+  }
+}
--- a/vllm-serve/values.yaml
+++ b/vllm-serve/values.yaml
@ -0,0 +1,76 @@
+# Default values for vllm-app.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
+imagePullSecrets: []
+imagePullPolicy: IfNotPresent
+# This is to override the chart name.
+nameOverride: ""
+fullnameOverride: ""
+
+# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Automatically mount a ServiceAccount's API credentials?
+  automount: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+  
+  
+# 模型配置
+model:
+  huggingfaceName: "Qwen/Qwen2.5-0.5B-Instruct"  # 用户只需输入这个
+  localMountPath: "/Model"                  # PVC 固定挂载路径
+  huggingfaceToken: "<your-hf-token>"
+  download:                               # 启用自动下载
+    image: "docker.io/vllm/vllm-openai:latest"  # 包含 huggingface-cli 的镜像
+
+# 功能选择
+
+resources:
+  gpuLimit: 1
+  cpuRequest: 12
+  memoryLimit: "16Gi"
+  shmSize: "20Gi"
+
+svc:
+  type: LoadBalancer
+  port: 80 
+  targetPort: 8000 
+  # nodePort: 30080 
+# vLLM 应用配置
+vllm:
+  image: "docker.io/vllm/vllm-openai:latest"
+
+command: ""
+
+llama:
+  image: "docker.io/library/one-click:v1"
+
+# lmdeploy  应用配置
+lmdeploy:
+  image: "docker.io/openmmlab/lmdeploy:latest-cu12"
+
+
+# NFS PV/PVC 配置
+nfs:
+  server: "10.6.80.11"
+  path: "/volume1/Dataset/PVStore/lab-data-model-pvc-c0beeab1-6dd5-4c6a-bd2c-6ce9e114c25e/Weight"
+  # storageClass: "local-path"
+  pvSize: "500Gi"
+  pvcSize: "50Gi"
+
+# LeaderWorkerSet 配置
+replicaCount: 1
+workerSize: 1
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}