Kubernetes与AI推理服务最佳实践 | 极客日志

Kubernetes与AI推理服务最佳实践 | 极客日志

# 安装NVIDIA驱动（在节点上执行） apt-get install -y nvidia-driver-535 # 安装NVIDIA Device Plugin kubectl apply -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.0/nvidia-device-plugin.yml # 验证GPU资源 kubectl get nodes -o jsonpath='{range .items[*]}{.metadata.name}{"\t":.status.capacity.nvidia\.com/gpu}{"\n"}{end}'

apiVersion: apps/v1 kind: Deployment metadata: name: tensorflow-serving namespace: default spec: replicas: 2 selector: matchLabels: app: tensorflow-serving template: metadata: labels: app: tensorflow-serving spec: containers: - name: tensorflow-serving image: tensorflow/serving:latest ports: - containerPort: 8501 resources: limits: nvidia.com/gpu: 1 requests: nvidia.com/gpu: 1 volumeMounts: - name: model-volume mountPath: /models volumes: - name: model-volume persistentVolumeClaim: claimName: model-pvc

# 下载示例模型 mkdir -p models/mnist/1 wget -O models/mnist/1/saved_model.pb https://storage.googleapis.com/download.tensorflow.org/models/official/20181001_resnet/savedmodels/resnet_v2_fp32_savedmodel_NHWC_jpg.tar.gz # 创建模型存储 kubectl create -f - <<EOF apiVersion: v1 kind: PersistentVolumeClaim metadata: name: model-pvc namespace: default spec: accessModes: - ReadWriteOnce resources: requests: storage: 10Gi EOF

apiVersion: apps/v1 kind: Deployment metadata: name: tf-serving namespace: default spec: replicas: 2 selector: matchLabels: app: tf-serving template: metadata: labels: app: tf-serving spec: containers: - name: tf-serving image: tensorflow/serving:latest ports: - containerPort: 8500 - containerPort: 8501 env: - name: MODEL_NAME value: mnist volumeMounts: - name: model-volume mountPath: /models volumes: - name: model-volume persistentVolumeClaim: claimName: model-pvc

apiVersion: v1 kind: Service metadata: name: tf-serving namespace: default spec: selector: app: tf-serving ports: - port: 8501 targetPort: 8501 type: LoadBalancer

# 部署服务 kubectl apply -f deployment.yaml kubectl apply -f service.yaml # 测试推理服务 MODEL_SERVICE=$(kubectl get svc tf-serving -o jsonpath='{.status.loadBalancer.ingress[0].ip}') curl -d '{"instances": [[[0.0 for _ in range(28)] for _ in range(28)]]}' -X POST http://$MODEL_SERVICE:8501/v1/models/mnist:predict

apiVersion: apps/v1 kind: Deployment metadata: name: triton-server namespace: default spec: replicas: 2 selector: matchLabels: app: triton-server template: metadata: labels: app: triton-server spec: containers: - name: triton-server image: nvcr.io/nvidia/tritonserver:23.08-py3 ports: - containerPort: 8000 - containerPort: 8001 - containerPort: 8002 resources: limits: nvidia.com/gpu: 1 requests: nvidia.com/gpu: 1 volumeMounts: - name: model-volume mountPath: /models volumes: - name: model-volume persistentVolumeClaim: claimName: model-pvc

apiVersion: v1 kind: Service metadata: name: triton-server namespace: default spec: selector: app: triton-server ports: - port: 8000 targetPort: 8000 - port: 8001 targetPort: 8001 - port: 8002 targetPort: 8002 type: LoadBalancer

# 部署服务 kubectl apply -f deployment.yaml kubectl apply -f service.yaml # 检查服务状态 kubectl get pods -l app=triton-server

apiVersion: apps/v1 kind: Deployment metadata: name: tf-serving-batched namespace: default spec: replicas: 2 selector: matchLabels: app: tf-serving-batched template: metadata: labels: app: tf-serving-batched spec: containers: - name: tf-serving image: tensorflow/serving:latest ports: - containerPort: 8501 env: - name: MODEL_NAME value: mnist - name: TF_FORCE_GPU_ALLOW_GROWTH value: "true" - name: BATCH_SIZE value: "32" resources: limits: nvidia.com/gpu: 1 requests: nvidia.com/gpu: 1

apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: name: tf-serving-hpa namespace: default spec: scaleTargetRef: apiVersion: apps/v1 kind: Deployment name: tf-serving minReplicas: 2 maxReplicas: 10 metrics: - type: Resource resource: name: cpu target: type: Utilization averageUtilization: 70 - type: Resource resource: name: memory target: type: Utilization averageUtilization: 80

apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor metadata: name: tf-serving-monitor namespace: monitoring spec: selector: matchLabels: app: tf-serving endpoints: - port: 8501 path: /v1/monitoring/prometheus interval: 15s

apiVersion: apps/v1 kind: Deployment metadata: name: tf-serving namespace: default spec: # ... template: spec: containers: - name: tf-serving image: tensorflow/serving:latest # ... env: - name: TF_CPP_MIN_LOG_LEVEL value: "0" - name: TF_ENABLE_GPU_GARBAGE_COLLECTION value: "true" args: - --model_name=mnist - --model_base_path=/models/mnist - --enable_batching=true - --batching_parameters_file=/models/batching_parameters.txt

apiVersion: networking.k8s.io/v1 kind: NetworkPolicy metadata: name: ai-inference-network-policy namespace: default spec: podSelector: matchLabels: app: tf-serving policyTypes: - Ingress - Egress ingress: - from: - podSelector: matchLabels: app: api-gateway ports: - protocol: TCP port: 8501 egress: - to: - podSelector: matchLabels: app: monitoring ports: - protocol: TCP port: 9090

apiVersion: apps/v1 kind: Deployment metadata: name: triton-multi-model namespace: default spec: replicas: 2 selector: matchLabels: app: triton-multi-model template: metadata: labels: app: triton-multi-model spec: containers: - name: triton-server image: nvcr.io/nvidia/tritonserver:23.08-py3 ports: - containerPort: 8000 - containerPort: 8001 - containerPort: 8002 resources: limits: nvidia.com/gpu: 1 requests: nvidia.com/gpu: 1 volumeMounts: - name: model-volume mountPath: /models volumes: - name: model-volume persistentVolumeClaim: claimName: models-pvc

apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: ai-inference-ingress namespace: default annotations: nginx.ingress.kubernetes.io/canary: "true" nginx.ingress.kubernetes.io/canary-weight: "20" spec: rules: - host: inference.example.com http: paths: - path: /v1/models pathType: Prefix backend: service: name: tf-serving-v2 port: number: 8501

# 查看GPU使用情况 kubectl exec -it <pod-name> -- nvidia-smi # 查看推理服务日志 kubectl logs -l app=tf-serving # 检查模型状态 curl http://<service-ip>:8501/v1/models/mnist # 测试推理服务 curl -d '{"instances": [[[0.0 for _ in range(28)] for _ in range(28)]]}' -X POST http://<service-ip>:8501/v1/models/mnist:predict