vllm-omni/.buildkite/test-weekly.yml

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

  - label: "Reliability Test - hunyuan-image"
    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_hunyuan_image.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: 4
                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 - voxcpm2"
    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_voxcpm2.py -m "slow"
    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"

  # 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"

  - group: ":card_index_dividers: E2E Tests"
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    steps:
      - label: "Omni · L4"
        timeout_in_minutes: 90
        commands:
          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
          - pytest -s -v tests/e2e/*/test_qwen2_5_omni_expansion.py --run-level "core_model"
          - >-
            pytest -s -v tests/e2e/
            --ignore=tests/e2e/online_serving/test_qwen2_5_omni_expansion.py
            --ignore=tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py
            -m "slow and L4 and omni"
            --run-level "full_model"
        agents:
          queue: "gpu_4_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"

      - label: "Omni · H100"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and H100 and omni"
            --run-level "full_model"
        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: "TTS · L4"
        timeout_in_minutes: 90
        commands:
          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
          - export VLLM_USE_DEEP_GEMM="0"
          - export VLLM_MOE_USE_DEEP_GEMM="0"
          - |
            failed=0
            for f in $(pytest --collect-only -q tests/e2e/ -m "slow and L4 and tts" --run-level "full_model" | grep '\.py::' | sed -E 's|::.*||' | sort -u); do
              pytest -s -v "$$f" -m "slow and L4 and tts" --run-level "full_model" || failed=1
            done
            exit $$failed
        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"

      - label: "TTS · H100"
        timeout_in_minutes: 90
        commands:
          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
          - export VLLM_USE_DEEP_GEMM="0"
          - export VLLM_MOE_USE_DEEP_GEMM="0"
          - >-
            pytest -sv
            tests/e2e/ -m "slow and H100 and tts"
            --run-level "full_model"
        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: 1
                    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: "Diffusion · L4"
        timeout_in_minutes: 60
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and L4"
            --run-level "full_model"
        agents:
          queue: "gpu_4_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"

      - label: "Diffusion · H100 · Single-GPU"
        timeout_in_minutes: 120
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and H100 and not distributed_cuda"
            --run-level "full_model"
        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: 1
                    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: "Diffusion · H100 · Multi-GPU"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and H100 and distributed_cuda"
            --run-level "full_model"
        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