application-serve-mistral-7b.yaml

---
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  labels:
    app: serve-mistral-7b
  name: serve-mistral-7b
  namespace: openshift-gitops
spec:
  destination:
    server: 'https://kubernetes.default.svc'
  project: default
  source:
    path: gitops/model
    repoURL: https://github.com/alvarolop/model-serving-utils.git
    targetRevision: main
    helm:
      values: |
        dataScienceProjectDisplayName: mistral-7b
        dataScienceProjectNamespace: mistral-7b
        instanceName: mistral-7b
        model:
          root: mistralai
          id: Mistral-7B-Instruct-v0.2
          name: mistral-7b
          displayName: Mistral 7b
          # additionalLabels:
          #   networking.knative.dev/visibility: cluster-local
          toolCallParser: mistral
          maxModelLen: '6144'
          runtime: 
            resources:
              limits:
                cpu: '8'
                memory: 24Gi
              requests:
                cpu: '6'
                memory: 24Gi
            image: quay.io/modh/vllm@sha256:c86ff1e89c86bc9821b75d7f2bbc170b3c13e3ccf538bf543b1110f23e056316
          accelerator:
            productName: NVIDIA-A10G-SHARED
  syncPolicy:
    automated:
      prune: false
      selfHeal: false
    syncOptions:
      - CreateNamespace=true