sessions/next25/agentic-rag/ollama-cloud-run/service.yaml

apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  name: llama-service-model-preloaded # Replace with your desired service name
  annotations:
    run.googleapis.com/launch-stage: ALPHA
spec:
  template:
    metadata:
      annotations:
        run.googleapis.com/execution-environment: gen2
        autoscaling.knative.dev/maxScale: '1'
        run.googleapis.com/cpu-throttling: 'false'
        run.googleapis.com/startup-cpu-boost: 'true'
    spec: 
      nodeSelector:
        run.googleapis.com/accelerator: "nvidia-l4"
      containers:
        - name: ollama
          image: gcr.io/genai-playground24/ollama-preloaded:tag1 
          ports:
            - containerPort: 11434
          env:
          resources:
            limits:
              cpu: '6.0'
              memory: '24Gi'
              nvidia.com/gpu: '1'