vllm-omni/.buildkite/npu/test-npu-ready.yml

steps:
  - group: ":card_index_dividers: Simple Test"
    depends_on: upload-ready-pipeline
    steps:
      - label: "Platforms Test"
        key: ready-platforms-test
        mirror_hardwares: a3_npu_2
        commands:
          - >-
            pytest -s -v
            tests/platforms/npu/test_minicpmo_code2wav_npugraph.py
            -m 'core_model and npu and A3 and omni'
            --run-level 'core_model'

      - label: "Diffusion NPU layer tests - A2"
        key: ready-diffusion-npu-layer-tests-a2
        mirror_hardwares: a2b3_npu_1
        commands:
          - >-
            pytest -s -v
            tests/diffusion/layers/test_activation.py
            -m 'core_model and npu and A2'
            --run-level 'core_model'

      - label: "Diffusion NPU layer tests - A3"
        key: ready-diffusion-npu-layer-tests
        mirror_hardwares: a3_npu_2
        commands:
          - >-
            pytest -s -v
            tests/diffusion/layers/test_activation.py
            tests/diffusion/layers/test_fused_qk_norm_rope_npu.py
            tests/diffusion/models/minimax_h3/test_minimax_h3_qwen3vl_swiglu.py
            tests/diffusion/models/minimax_h3/test_minimax_h3_modulation.py
            -m 'core_model and npu and A3'
            --run-level 'core_model'

      - label: "Diffusion NPU layer tests - A5"
        key: ready-diffusion-npu-layer-tests-a5
        mirror_hardwares: a5_npu_2
        commands:
          - >-
            pytest -s -v
            tests/diffusion/layers/test_activation.py
            -m 'core_model and npu and A5'
            --run-level 'core_model'

      - label: "Diffusion NPU layer tests - 310P"
        key: ready-diffusion-npu-layer-tests-310p
        mirror_hardwares: 310p_npu_1
        commands:
          - >-
            pytest -s -v
            tests/diffusion/layers/test_activation.py
            -m 'core_model and npu and 310P'
            --run-level 'core_model'

  - group: ":card_index_dividers: E2E Test"
    key: ready-e2e-group
    depends_on: upload-ready-pipeline
    steps:
      - label: "Omni · MiniCPM-o 4.5 Test"
        mirror_hardwares: a3_npu_2
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'

      - label: "Omni · MiniCPM-o 4.5 Duplex Test"
        mirror_hardwares: a3_npu_2
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
          - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'

      - label: "Omni · MiniCPM-o 4.5 Perf Test"
        timeout_in_minutes: 60
        mirror_hardwares: a3_npu_2
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
          - export BENCHMARK_DIR=tests/dfx/perf/results
          - pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5_ready.json -m 'core_model and npu and A3 and omni'

      - label: "Omni · Qwen3-Omni Test"
        mirror_hardwares: a3_npu_4
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
          - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
        timeout_in_minutes: 60

      - label: ":sound: TTS · Qwen3-TTS CustomVoice Test"
        mirror_hardwares: a3_npu_2
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
          HF_TOKEN: "${HF_TOKEN}"
        commands:
          - pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model and npu' --run-level 'core_model'

      - label: "Diffusion · HunyuanVideo-1.5 Test"
        mirror_hardwares: a3_npu_2
        env:
            VLLM_WORKER_MULTIPROC_METHOD: spawn
            VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
            - |
              timeout 40m bash -c "
                export VLLM_IMAGE_FETCH_TIMEOUT=60
                pytest -s -v tests/e2e/online_serving/test_hunyuan_video_15_expansion.py -m 'core_model and diffusion and npu' --run-level 'core_model'
                "
        timeout_in_minutes: 60

      - label: "Diffusion · Qwen Image Test"
        mirror_hardwares: a3_npu_2
        env:
            VLLM_WORKER_MULTIPROC_METHOD: spawn
            VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        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 and npu' --run-level 'core_model'
                "
        timeout_in_minutes: 60

      - label: "Diffusion · Wan22 Test"
        mirror_hardwares: a3_npu_2
        env:
            VLLM_WORKER_MULTIPROC_METHOD: spawn
            VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        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 and npu' --run-level 'core_model'
                "
        timeout_in_minutes: 60

      - label: "Diffusion · Hunyuan Image Test"
        mirror_hardwares: a3_npu_4
        env:
            VLLM_WORKER_MULTIPROC_METHOD: spawn
            VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
        commands:
            - |
                timeout 40m bash -c "
                export VLLM_IMAGE_FETCH_TIMEOUT=60
                pytest -s -v tests/e2e/online_serving/test_hunyuan_image.py -m 'core_model and diffusion and npu' --run-level 'core_model'
                "
        timeout_in_minutes: 60