基于阿里云 Serverless 容器服务轻松部署企业级 AI 应用

apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  name: knative-sd-demo
  annotations:
    serving.knative.dev.alibabacloud/affinity: "cookie"
    serving.knative.dev.alibabacloud/cookie-name: "sd"
    serving.knative.dev.alibabacloud/cookie-timeout: "1800"
spec:
  template:
    metadata:
      annotations:
        autoscaling.knative.dev/class: mpa.autoscaling.knative.dev
        autoscaling.knative.dev/maxScale: '10'
        autoscaling.knative.dev/targetUtilizationPercentage: "100"
        k8s.aliyun.com/eci-use-specs: ecs.gn5-c4g1.xlarge,ecs.gn5i-c8g1.2xlarge,ecs.gn5-c8g1.2xlarge  
    spec:
      containerConcurrency: 1
      containers:
      - args:
        - --listen
        - --skip-torch-cuda-test
        - --api
        command:
        - python3
        - launch.py
        image: yunqi-registry.cn-shanghai.cr.aliyuncs.com/lab/stable-diffusion@sha256:64999ff1aba706f65a2234d861d46318f7d58e2790b31ace0d567a96e65b617c
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 7860
          name: http1
          protocol: TCP
        name: stable-diffusion
        readinessProbe:
          tcpSocket:
            port: 7860
          initialDelaySeconds: 5
          periodSeconds: 1
          failureThreshold: 3

---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: portal-server
  name: portal-server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: portal-server
  template:
    metadata:
      labels:
        app: portal-server
    spec:
      serviceAccountName: portal-server
      containers:
        - name: portal-server
          image: registry-vpc.cn-beijing.aliyuncs.com/acs/sd-yunqi-server:v1.0.2
          imagePullPolicy: IfNotPresent
          env:
            - name: MAX_CONCURRENT_REQUESTS
              value: "5"
            - name: POD_NAMESPACE
              value: "default"
          readinessProbe:
            failureThreshold: 3
            periodSeconds: 1
            successThreshold: 1
            tcpSocket:
              port: 8080
            timeoutSeconds: 1
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    service.beta.kubernetes.io/alibaba-cloud-loadbalancer-address-type: internet
    service.beta.kubernetes.io/alibaba-cloud-loadbalancer-instance-charge-type: PayByCLCU
  name: portal-server
spec:
  externalTrafficPolicy: Local
  ports:
    - name: http-80
      port: 80
      protocol: TCP
      targetPort: 8080
    - name: http-8888
      port: 8888
      protocol: TCP
      targetPort: 8888
  selector:
    app: portal-server
  type: LoadBalancer
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: pod-list-cluster-role
rules:
  - apiGroups: [""]
    resources: ["pods"]
    verbs: ["list"]
  - apiGroups: ["networking.k8s.io"]
    resources: ["ingresses"]
    verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: pod-list-cluster-role-binding
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: pod-list-cluster-role
subjects:
  - kind: ServiceAccount
    name: portal-server
    namespace: default
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: portal-server
  namespace: default