replicaCount: 1

image:
  repository: vllm/vllm-openai
  tag: latest
  pullPolicy: Always

resources:
  limits:
    nvidia.com/gpu: 1
  requests:
    cpu: "2"
    memory: "8Gi"

runtimeClassName: nvidia

env:
  - name: HF_TOKEN
    valueFrom:
      secretKeyRef:
        name: vllm-secrets
        key: HF_TOKEN

args:
  - "serve"
  - "numind/NuExtract3"
  - "--served-model-name"
  - "numind/NuExtract3"
  - "--host"
  - "0.0.0.0"
  - "--port"
  - "8000"
  - "--gpu-memory-utilization"
  - "0.45"
  - "--max-model-len"
  - "8192"
  - "--max-num-seqs"
  - "8"

service:
  type: ClusterIP
  port: 8000

nodeSelector:
  kubernetes.io/hostname: gremlin-1