apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  annotations:
    serving.kserve.io/deploymentMode: RawDeployment
  labels:
    app.kubernetes.io/name: llm-verifier
    app.kubernetes.io/part-of: llm-serving
  name: verifier
  namespace: llm-serving
spec:
  predictor:
    containers:
    - args:
      - --model=Qwen/Qwen2.5-Math-PRM-7B
      - --served-model-name=verifier
      - --runner=pooling
      - --dtype=float16
      - --tensor-parallel-size=1
      - --max-model-len=4096
      - --max-num-seqs=8
      - --host=0.0.0.0
      - --port=8080
      env:
      - name: VLLM_USE_FLASHINFER_SAMPLER
        value: '0'
      - name: VLLM_ATTENTION_BACKEND
        value: XFORMERS
      - name: HF_HOME
        value: /mnt/models
      image: vllm/vllm-openai:v0.11.0@sha256:014a95f21c9edf6abe0aea6b07353f96baa4ec291c427bb1176dc7c93a85845c
      name: kserve-container
      ports:
      - containerPort: 8080
        protocol: TCP
      readinessProbe:
        httpGet:
          path: /health
          port: 8080
        periodSeconds: 10
      resources:
        limits:
          cpu: '16'
          memory: 16Gi
          nvidia.com/gpu: '1'
        requests:
          cpu: '4'
          memory: 8Gi
          nvidia.com/gpu: '1'
      startupProbe:
        failureThreshold: 60
        httpGet:
          path: /health
          port: 8080
        periodSeconds: 15
      volumeMounts:
      - mountPath: /mnt/models
        name: models
      - mountPath: /dev/shm
        name: shm
    deploymentStrategy:
      type: Recreate
    maxReplicas: 1
    minReplicas: 1
    nodeSelector:
      kubernetes.io/hostname: worker-1
    runtimeClassName: nvidia
    volumes:
    - name: models
      persistentVolumeClaim:
        claimName: llm-models
    - emptyDir:
        medium: Memory
        sizeLimit: 1Gi
      name: shm