vllm-omni/.buildkite/cuda/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: "Simple · CPU Coverage Test"
    key: weekly-simple-cpu-coverage
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1"
    timeout_in_minutes: 60
    commands:
      - |
        set +e
        REPORT="coverage-core-model-cpu-$${BUILDKITE_STEP_ID:-local}.xml"
        pytest -sv tests/ -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml:$${REPORT}
        EXIT=$$?
        gzip -9 -f "$${REPORT}"
        buildkite-agent artifact upload "$${REPORT}.gz"
        exit $$EXIT
    mirror_hardwares: l4_1

  - group: "Reliability Test"
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    steps:

      - label: "Reliability Test · qwen3-omni"
        timeout_in_minutes: 180
        commands:
          - pytest -s -v tests/dfx/reliability/test_reliability_qwen3_omni.py -m "slow"
        mirror_hardwares: h100_2

      - label: "Reliability Test · wan22"
        timeout_in_minutes: 180
        commands:
          - pytest -s -v tests/dfx/reliability/test_reliability_wan22.py -m "slow"
        mirror_hardwares: h100_2

      - label: "Reliability Test · hunyuan-image"
        timeout_in_minutes: 180
        commands:
          - pytest -s -v tests/dfx/reliability/test_reliability_hunyuan_image.py -m "slow"
        mirror_hardwares: h100_4

      - label: "Reliability Test · Invalid parameters · H100 · Single-GPU"
        timeout_in_minutes: 90
        commands:
          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100 and cards_1"
        mirror_hardwares: h100_1

      - label: "Reliability Test · Invalid parameters · H100 · 2-GPU"
        timeout_in_minutes: 90
        commands:
          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100 and cards_2"
        mirror_hardwares: h100_2

      - label: "Reliability Test · Invalid parameters · L4"
        timeout_in_minutes: 120
        commands:
          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"
        mirror_hardwares: l4_1

  - group: "Perf Test"
    depends_on: upload-weekly-pipeline
    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
    steps:

      - label: ":full_moon: Omni · Perf Test · vLLM Text"
        key: weekly-omni-performance-vllm-text
        timeout_in_minutes: 180
        commands:
          - export BENCHMARK_DIR=tests/dfx/perf/results
          - |
            set +e
            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
            EXIT=$$?
            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
            exit $$EXIT
        mirror_hardwares: h100_2

      - label: ":full_moon: Omni · Perf Test · Async Chunk · Random"
        key: weekly-omni-performance-async-chunk-random
        timeout_in_minutes: 180
        commands:
          - export BENCHMARK_DIR=tests/dfx/perf/results
          - |
            set +e
            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json -m "H100 and slow"
            EXIT=$$?
            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
            exit $$EXIT
        mirror_hardwares: h100_2

      - label: ":full_moon: Omni · Perf Test · Multi-Replica"
        key: weekly-omni-performance-multi-replicas
        timeout_in_minutes: 180
        commands:
          - export BENCHMARK_DIR=tests/dfx/perf/results
          - |
            set +e
            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
            EXIT=$$?
            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
            exit $$EXIT
        mirror_hardwares: h100_3

  - group: ":card_index_dividers: E2E Tests"
    depends_on: upload-weekly-pipeline
    if: build.env("NON_CRITICAL") == "1"
    steps:

      # Qwen2.5 expansion (CUDA 4-card / online 2-card) stays on this l4_4 job.
      - label: "Omni · L4 · Multi-GPU"
        timeout_in_minutes: 90
        commands:
          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
          - pytest -s -v tests/e2e/*/test_qwen2_5_omni_expansion.py -m "slow and L4 and omni and not cards_1" --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 and not cards_1"
            --run-level "full_model"
        mirror_hardwares: l4_4

      - label: "Omni · H100 · Single-GPU"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and H100 and omni and cards_1"
            --run-level "full_model"
        mirror_hardwares: h100_1

      - label: "Omni · H100 · 4-GPU"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and H100 and omni and cards_4"
            --run-level "full_model"
        mirror_hardwares: h100_4

      - label: "TTS · L4"
        timeout_in_minutes: 120
        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
        mirror_hardwares: l4_1

      - 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"
        mirror_hardwares: h100_1

      # Own step: the image has no NanoCodec, so this file import-skips out of
      # the mark-selected TTS steps above. The overrides keep nemo_toolkit[tts]
      # from downgrading transformers; see
      # examples/offline_inference/text_to_speech/README.md.
      - label: "TTS · Gepard-1.0 · L4"
        timeout_in_minutes: 60
        commands:
          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
          - printf '%s\n' "transformers>=5.5.3" "huggingface-hub>=1.0" > /tmp/gepard-overrides.txt
          - uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" "nemo_toolkit[tts]==2.7.3" --overrides /tmp/gepard-overrides.txt
          - >-
            pytest -s -v tests/e2e/offline_inference/test_gepard_tts.py
            -m "tts and cuda"
            --run-level "full_model"
        mirror_hardwares: l4_1

      - label: "Diffusion · L4 · Single-GPU"
        timeout_in_minutes: 60
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and L4 and cards_1"
            --run-level "full_model"
        mirror_hardwares: l4_1

      - label: "Diffusion · L4 · Multi-GPU"
        timeout_in_minutes: 60
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and L4 and not cards_1"
            --run-level "full_model"
        mirror_hardwares: l4_4

      - label: "Diffusion · H100 · Single-GPU"
        timeout_in_minutes: 150
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and H100 and cards_1"
            --run-level "full_model"
        mirror_hardwares: h100_1

      - label: "Diffusion · H100 · 2-GPU"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and H100 and cards_2"
            --run-level "full_model"
        mirror_hardwares: h100_2

      - label: "Diffusion · H100 · 4-GPU"
        timeout_in_minutes: 90
        commands:
          - >-
            pytest -sv
            tests/e2e/ -m "slow and diffusion and H100 and cards_4"
            --run-level "full_model"
        mirror_hardwares: h100_4