env:
  VLLM_WORKER_MULTIPROC_METHOD: spawn
  VLLM_USE_FLASHINFER_MOE_FP16: 0
  HF_HUB_DOWNLOAD_TIMEOUT: 300
  HF_HUB_ETAG_TIMEOUT: 60

steps:
  - label: "Reliability Test - qwen3-omni"
    timeout_in_minutes: 180
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    commands:
      - pytest -s -v tests/dfx/reliability/test_reliability_qwen3_omni.py -m "slow"
    agents:
      queue: "mithril-h100-pool"
    plugins:
      - kubernetes:
          podSpec:
            containers:
              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                resources:
                  limits:
                    nvidia.com/gpu: 2
                volumeMounts:
                  - name: devshm
                    mountPath: /dev/shm
                  - name: hf-cache
                    mountPath: /root/.cache/huggingface
                env:
                  - name: HF_HOME
                    value: /root/.cache/huggingface
                  - name: HF_TOKEN
                    valueFrom:
                      secretKeyRef:
                        name: hf-token-secret
                        key: token
            nodeSelector:
              node.kubernetes.io/instance-type: gpu-h100-sxm
            volumes:
              - name: devshm
                emptyDir:
                  medium: Memory
              - name: hf-cache
                hostPath:
                  path: /mnt/hf-cache
                  type: DirectoryOrCreate

  - label: "Reliability Test - wan22"
    timeout_in_minutes: 180
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    commands:
      - pytest -s -v tests/dfx/reliability/test_reliability_wan22.py -m "slow"
    agents:
      queue: "mithril-h100-pool"
    plugins:
      - kubernetes:
          podSpec:
            containers:
              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                resources:
                  limits:
                    nvidia.com/gpu: 2
                volumeMounts:
                  - name: devshm
                    mountPath: /dev/shm
                  - name: hf-cache
                    mountPath: /root/.cache/huggingface
                env:
                  - name: HF_HOME
                    value: /root/.cache/huggingface
                  - name: HF_TOKEN
                    valueFrom:
                      secretKeyRef:
                        name: hf-token-secret
                        key: token
            nodeSelector:
              node.kubernetes.io/instance-type: gpu-h100-sxm
            volumes:
              - name: devshm
                emptyDir:
                  medium: Memory
              - name: hf-cache
                hostPath:
                  path: /mnt/hf-cache
                  type: DirectoryOrCreate

  # Invalid HTTP / WS payloads vs live Omni servers (Issue #3649 tracks known skips).
  - group: "Reliability Test - Invalid parameters Test"
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    steps:
      - label: "Invalid parameters Test · H100"
        timeout_in_minutes: 120
        commands:
          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100"
        agents:
          queue: "mithril-h100-pool"
        plugins:
          - kubernetes:
              podSpec:
                containers:
                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                    resources:
                      limits:
                        nvidia.com/gpu: 2
                    volumeMounts:
                      - name: devshm
                        mountPath: /dev/shm
                      - name: hf-cache
                        mountPath: /root/.cache/huggingface
                    env:
                      - name: HF_HOME
                        value: /root/.cache/huggingface
                      - name: HF_TOKEN
                        valueFrom:
                          secretKeyRef:
                            name: hf-token-secret
                            key: token
                nodeSelector:
                  node.kubernetes.io/instance-type: gpu-h100-sxm
                volumes:
                  - name: devshm
                    emptyDir:
                      medium: Memory
                  - name: hf-cache
                    hostPath:
                      path: /mnt/hf-cache
                      type: DirectoryOrCreate

      # Stable Audio Open, Qwen3-TTS speech/batch/voices paths marked ``L4``.
      - label: "Invalid parameters Test · L4"
        timeout_in_minutes: 120
        commands:
          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"
        agents:
          queue: "gpu_1_queue"
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              shm-size: "8gb"
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"