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

steps:
  - group: ":card_index_dividers: Simple Test"
    depends_on: upload-ready-pipeline
    steps:
      - label: "Simple · Diffusion & Model Executor Test"
        commands:
          - "timeout 20m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
        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
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

      - label: "Simple · Other Test"
        commands:
          - "timeout 20m pytest -sv -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
        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
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

  - label: "Custom Pipeline Test"
    depends_on: upload-ready-pipeline
    commands:
      - timeout 20m pytest -s -v tests/e2e/offline_inference/custom_pipeline/ -m "core_model"
    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
          environment:
            - "HF_HOME=/fsx/hf_cache"
          volumes:
            - "/fsx/hf_cache:/fsx/hf_cache"

  - group: ":card_index_dividers: Diffusion Test"
    depends_on: upload-ready-pipeline
    steps:
      - label: "Diffusion · Offloader Test"
        commands:
          - timeout 40m pytest -s -v tests/diffusion/offloader -m "core_model and cuda" --run-level "core_model"
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

      - label: "Diffusion · Cache Test"
        commands:
          - timeout 15m pytest -sv tests/diffusion/cache -m 'core_model and cuda' --run-level "core_model"
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

      - label: "Diffusion · Batch Test"
        commands:
          - timeout 15m pytest -sv tests/diffusion/batching -m 'core_model and cuda' --run-level "core_model"
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

      - label: "Diffusion · Distributed Test"
        commands:
          - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda' --run-level "core_model"
        agents:
          queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
        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 · Model Test"
        commands:
          - timeout 15m pytest -sv tests/diffusion/models/ -m 'core_model and cuda' --run-level "core_model"
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

      - label: "Diffusion · Other Test"
        commands:
          - timeout 15m pytest -sv tests/diffusion/*.py -m 'core_model and cuda' --run-level "core_model"
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"


  - group: ":card_index_dividers: Tiny Model Tests [Single GPU]"
    depends_on: upload-ready-pipeline
    steps:
      - label: "Tiny Model Tests · Diffusion (base)"
        commands:
          - timeout 15m pytest -sv tests/model_tests/diffusion -m 'core_model and cuda' --run-level "core_model"
        agents:
          # Ready label only runs the cases that don't need parallelism for tiny
          # model tests, which is usually just a smoke test for TTI and I2I
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"

  - label: "Engine&Model Executor Test"
    depends_on: upload-ready-pipeline
    commands:
      - |
        timeout 15m bash -c "
                  pytest -sv tests/engine/ tests/model_executor/ -m 'core_model and cuda' --run-level 'core_model'
        "
    agents:
      queue: "gpu_1_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
    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: "Distributed Test"
    depends_on: upload-ready-pipeline
    commands:
      - |
        timeout 20m bash -c "
          pytest -sv tests/distributed/ -m 'core_model and cuda and L4' --run-level 'core_model'
        "
    agents:
      queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
    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: "Entrypoints Test"
    depends_on: upload-ready-pipeline
    commands:
      - |
        timeout 30m bash -c "
          export VLLM_WORKER_MULTIPROC_METHOD=spawn
          pytest -sv tests/entrypoints/ -m 'core_model and cuda' --run-level 'core_model'
        "
    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 Test"
    depends_on: upload-ready-pipeline
    steps:
      - label: "RLHF · VeRL-Omni E2E Test"
        source_file_dependencies:
          - tests/e2e/offline_inference/rlhf_test/test_verl_omni_e2e.py
          - tests/e2e/offline_inference/custom_pipeline/
          - vllm_omni/diffusion/
          - vllm_omni/engine/
          - vllm_omni/entrypoints/
          - vllm_omni/inputs/
          - vllm_omni/outputs/
        commands:
          - |
            timeout 20m bash -c "
              pytest -s -v tests/e2e/offline_inference/rlhf_test/test_verl_omni_e2e.py
            "
        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: "Omni · Qwen3-Omni Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen3_omni.py
          - vllm_omni/model_executor/models/qwen3_omni/
          - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
          - vllm_omni/deploy/qwen3_omni_moe.yaml
        commands:
          - |
            timeout 20m bash -c "
              pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m 'core_model' --run-level 'core_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
                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 · VoxCPM2 Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_voxcpm2_tts.py
          - vllm_omni/model_executor/models/voxcpm2/
          - vllm_omni/deploy/voxcpm2.yaml
        timeout_in_minutes: 30
        commands:
          - |
            timeout 30m bash -c "
              export VLLM_LOGGING_LEVEL=DEBUG
              export VLLM_WORKER_MULTIPROC_METHOD=spawn
              pytest -s -v tests/e2e/online_serving/test_voxcpm2_tts.py -m 'core_model' --run-level 'core_model'
            "
        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 · Qwen3-TTS CustomVoice Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen3_tts_customvoice.py
          - vllm_omni/model_executor/models/qwen3_tts/
          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
          - vllm_omni/deploy/qwen3_tts.yaml
        commands:
          - |
            timeout 20m bash -c "
              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model' --run-level 'core_model'
            "
        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 · Qwen3-TTS Base Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen3_tts_base.py
          - vllm_omni/model_executor/models/qwen3_tts/
          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
          - vllm_omni/deploy/qwen3_tts.yaml
        commands:
          - |
            timeout 20m bash -c "
              export VLLM_WORKER_MULTIPROC_METHOD=spawn
              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
              export VLLM_OMNI_USE_V2_RUNNER=1
              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m 'core_model' --run-level 'core_model'
            "
        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 · Higgs-Audio-V3 Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_higgs_audio_v3.py
          - vllm_omni/model_executor/models/higgs_audio_v3/
          - vllm_omni/model_executor/stage_input_processors/higgs_audio_v3.py
          - vllm_omni/deploy/higgs_multimodal_qwen3.yaml
        commands:
          - |
            timeout 20m bash -c "
              export VLLM_WORKER_MULTIPROC_METHOD=spawn
              export VLLM_USE_DEEP_GEMM=0
              export VLLM_MOE_USE_DEEP_GEMM=0
              pytest -s -v tests/e2e/online_serving/test_higgs_audio_v3.py -m 'core_model' --run-level 'core_model'
            "
        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: "Diffusion · Qwen Image Edit Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen_image_edit.py
          - vllm_omni/diffusion/models/qwen_image/
        commands:
          - |
            timeout 20m bash -c "
              pytest -s -v tests/e2e/online_serving/test_qwen_image_edit.py -m 'core_model' --run-level 'core_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
                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 · Bagel Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_bagel.py
          - vllm_omni/model_executor/models/bagel/
          - vllm_omni/diffusion/models/bagel/
          - vllm_omni/model_executor/stage_input_processors/bagel.py
          - vllm_omni/deploy/bagel.yaml
        commands:
          - |
            timeout 40m bash -c "
              export VLLM_IMAGE_FETCH_TIMEOUT=60
              pytest -s -v tests/e2e/online_serving/test_bagel.py -m 'core_model' --run-level 'core_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 · Wan22 Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_wan22_t2v.py
          - vllm_omni/diffusion/models/wan2_2/
        commands:
          - |
            timeout 40m bash -c "
              export VLLM_IMAGE_FETCH_TIMEOUT=60
              pytest -s -v tests/e2e/online_serving/test_wan22_t2v.py -m 'core_model' --run-level 'core_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 · Cosmos3 Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_cosmos3.py
          - vllm_omni/diffusion/models/cosmos3/
        commands:
          - |
            timeout 40m bash -c "
              export VLLM_IMAGE_FETCH_TIMEOUT=60
              pytest -s -v tests/e2e/online_serving/test_cosmos3.py -m 'core_model' --run-level 'core_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 · Qwen Image Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen_image.py
          - vllm_omni/diffusion/models/qwen_image/
        commands:
          - |
            timeout 40m bash -c "
              export VLLM_IMAGE_FETCH_TIMEOUT=60
              pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'core_model' --run-level 'core_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 · Qwen Image Layered Test"
        source_file_dependencies:
          - tests/e2e/online_serving/test_qwen_image_layered.py
          - vllm_omni/diffusion/models/qwen_image/
        commands:
          - |
            timeout 40m bash -c "
              export VLLM_IMAGE_FETCH_TIMEOUT=60
              pytest -s -v tests/e2e/online_serving/test_qwen_image_layered.py -m 'core_model' --run-level 'core_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 · GGUF Plugin Test"
        soft_fail: true
        source_file_dependencies:
          - tests/plugin/test_gguf_diffusion.py
          - vllm_omni/diffusion/model_loader
        commands:
          - pip install "vllm-gguf-plugin>=0.0.3"
          - timeout 30m pytest -sv tests/plugin/test_gguf_diffusion.py
        agents:
          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
        plugins:
          - docker#v5.2.0:
              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
              always-pull: true
              propagate-environment: true
              environment:
                - "HF_HOME=/fsx/hf_cache"
                - "HF_TOKEN"
              volumes:
                - "/fsx/hf_cache:/fsx/hf_cache"