vllm-omni/examples/online_serving/chart-helm/tests/deployment_test.yaml

suite: test deployment
templates:
  - deployment.yaml
tests:
  - it: should create deployment with default omni command
    asserts:
      - hasDocuments:
          count: 1
      - isKind:
          of: Deployment
      - equal:
          path: spec.template.spec.containers[0].name
          value: vllm-omni
      - equal:
          path: spec.template.spec.containers[0].command[0]
          value: vllm
      - equal:
          path: spec.template.spec.containers[0].command[1]
          value: serve
      - equal:
          path: spec.template.spec.containers[0].command[2]
          value: Tongyi-MAI/Z-Image-Turbo
      - equal:
          path: spec.template.spec.containers[0].command[3]
          value: "--omni"
      - equal:
          path: spec.template.spec.containers[0].command[4]
          value: "--host"
      - equal:
          path: spec.template.spec.containers[0].command[5]
          value: "0.0.0.0"
      - equal:
          path: spec.template.spec.containers[0].command[6]
          value: "--port"
      - equal:
          path: spec.template.spec.containers[0].command[7]
          value: "8000"

  - it: should use custom model when set
    set:
      model: "Qwen/Qwen2.5-Omni-7B"
    asserts:
      - equal:
          path: spec.template.spec.containers[0].command[2]
          value: Qwen/Qwen2.5-Omni-7B

  - it: should include omniArgs flags in command
    set:
      omniArgs:
        vaeUseSlicing: true
        vaeUseTiling: true
        enableCpuOffload: true
        numGpus: 2
        cacheBackend: "tea_cache"
        workerBackend: "ray"
        extraArgs:
          - "--enable-layerwise-offload"
    asserts:
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--vae-use-slicing"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--vae-use-tiling"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--enable-cpu-offload"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--num-gpus"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--cache-backend"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--worker-backend"
      - contains:
          path: spec.template.spec.containers[0].command
          content: "--enable-layerwise-offload"

  - it: should include deploy config in command
    set:
      omniArgs:
        deployConfigPath: "/configs/deploy.yaml"
    asserts:
      - equal:
          path: spec.template.spec.containers[0].command[8]
          value: "--deploy-config"
      - equal:
          path: spec.template.spec.containers[0].command[9]
          value: "/configs/deploy.yaml"

  - it: should reject removed stage config value
    set:
      omniArgs:
        stageConfigsPath: "/configs/legacy.yaml"
    asserts:
      - failedTemplate:
          errorMessage: "omniArgs.stageConfigsPath has been removed; use omniArgs.deployConfigPath"

  - it: should use full command override when image.command is set
    set:
      image:
        command:
          - "custom-binary"
          - "--flag"
    asserts:
      - equal:
          path: spec.template.spec.containers[0].command[0]
          value: custom-binary
      - equal:
          path: spec.template.spec.containers[0].command[1]
          value: "--flag"

  - it: should mount shm and model-cache volumes
    asserts:
      - contains:
          path: spec.template.spec.containers[0].volumeMounts
          content:
            name: shm
            mountPath: /dev/shm
      - contains:
          path: spec.template.spec.containers[0].volumeMounts
          content:
            name: model-cache
            mountPath: /cache
      - contains:
          path: spec.template.spec.volumes
          content:
            name: shm
            emptyDir:
              medium: Memory
              sizeLimit: 8Gi

  - it: should use PVC for model-cache when modelCache is enabled
    set:
      modelCache:
        enabled: true
        storageSize: "50Gi"
        accessModes:
          - ReadWriteOnce
    asserts:
      - contains:
          path: spec.template.spec.volumes
          content:
            name: model-cache
            persistentVolumeClaim:
              claimName: RELEASE-NAME-model-cache

  - it: should use emptyDir for model-cache when modelCache is disabled
    set:
      modelCache:
        enabled: false
        storageSize: "50Gi"
        accessModes:
          - ReadWriteOnce
    asserts:
      - contains:
          path: spec.template.spec.volumes
          content:
            name: model-cache
            emptyDir: {}

  - it: should set HF_HOME environment variable
    asserts:
      - contains:
          path: spec.template.spec.containers[0].env
          content:
            name: HF_HOME
            value: /cache/huggingface

  - it: should set HF_TOKEN env when hfToken is provided
    set:
      hfToken: "hf_test_token_123"
    asserts:
      - contains:
          path: spec.template.spec.containers[0].env
          content:
            name: HF_TOKEN
            valueFrom:
              secretKeyRef:
                name: RELEASE-NAME-hf-token
                key: token

  - it: should create custom init containers when specified
    set:
      extraInit:
        initContainers:
          - name: my-init
            image: busybox:latest
            command: ["echo", "init"]
    asserts:
      - lengthEqual:
          path: spec.template.spec.initContainers
          count: 1
      - equal:
          path: spec.template.spec.initContainers[0].name
          value: my-init
      - equal:
          path: spec.template.spec.initContainers[0].image
          value: busybox:latest