anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
e5c0afc99432dba767dcb66f28b0fb9aa43ab1af
vllm-omni/.buildkite/cuda/test-weekly.yml
T
Mengjie ZhaoandCursor c17126c219 [Model] Add Gepard-1.0 OpenAI /v1/audio/speech serving (#7499) 
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-15 14:56:51 -07:00

541 lines
21 KiB
YAML
Raw Blame History

# CUDA CI L5 (`slow` / reliability / extra coverage).
# Uploaded by Upload Weekly Pipeline: WEEKLY=1 / NON_CRITICAL=1, or PR label `weekly-test`.
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
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"
source_file_dependencies: omni_qwen3_omni_reliability
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"
source_file_dependencies: diffusion_wan22_reliability
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"
source_file_dependencies: diffusion_hunyuan_image3_reliability
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"
source_file_dependencies: reliability_invalid_param_h100
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"
source_file_dependencies: reliability_invalid_param_h100
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"
source_file_dependencies: reliability_invalid_param_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"
source_file_dependencies: omni_qwen3_omni_perf
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"
source_file_dependencies: omni_qwen3_omni_perf
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:
# Online Qwen2.5 expansion is 2-card; offline expansion + AutoRound are 4-card.
- label: "Omni · L4 · 2-GPU"
timeout_in_minutes: 90
commands:
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
- pytest -s -v tests/e2e/online_serving/test_qwen2_5_omni_expansion.py -m "slow and L4 and omni and cards_2" --run-level "core_model"
mirror_hardwares: l4_2
- label: "Omni · L4 · 4-GPU"
timeout_in_minutes: 90
commands:
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
- pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py -m "slow and L4 and omni and cards_4" --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 cards_4"
--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: 90
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
tests/e2e/online_serving/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 · 2-GPU"
timeout_in_minutes: 60
commands:
- >-
pytest -sv
tests/e2e/ -m "slow and diffusion and L4 and cards_2"
--run-level "full_model"
mirror_hardwares: l4_2
- label: "Diffusion · L4 · 4-GPU"
timeout_in_minutes: 60
commands:
- >-
pytest -sv
tests/e2e/ -m "slow and diffusion and L4 and cards_4"
--run-level "full_model"
mirror_hardwares: l4_4
# Split the old shared H100 Single-GPU sweep: one pytest process collected
# every slow+cards_1 diffusion file and exceeded 150 minutes.
- label: "Diffusion · Qwen-Image · H100 · Single-GPU"
timeout_in_minutes: 120
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_qwen_image_edit.py
tests/e2e/online_serving/test_qwen_image_edit_expansion.py
tests/e2e/online_serving/test_qwen_image_layered.py
tests/e2e/online_serving/test_qwen_image_layered_expansion.py
tests/e2e/accuracy/test_qwen_image_edit.py
tests/e2e/accuracy/test_qwen_image_layered.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Wan2.1 VACE · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_wan_2_1_vace_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · LongCat · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_longcat_image_expansion.py
tests/e2e/online_serving/test_longcat_image_edit_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Bagel · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_bagel.py
tests/e2e/online_serving/test_bagel_expansion.py
tests/e2e/offline_inference/test_bagel.py
tests/e2e/offline_inference/test_bagel_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Boogu · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_boogu_image.py
tests/e2e/online_serving/test_boogu_image_edit.py
tests/e2e/online_serving/test_boogu_image_expansion.py
tests/e2e/online_serving/test_boogu_image_edit_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Flux · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_flux_2_dev_expansion.py
tests/e2e/offline_inference/test_flux1_schnell_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · LTX · H100 · Single-GPU"
timeout_in_minutes: 120
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_ltx.py
tests/e2e/online_serving/test_ltx25.py
tests/e2e/accuracy/ltx/test_ltx_official_similarity.py
tests/e2e/accuracy/ltx/test_ltx25_official_similarity.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Krea2 · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_krea2_expansion.py
tests/e2e/offline_inference/test_krea2_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · HiDream-I1 · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_hidream_i1_full_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · SANA-Video · H100 · Single-GPU"
source_file_dependencies: diffusion_sana_video_function
timeout_in_minutes: 180
commands:
- export SANA_VIDEO_GOLDEN_BASE_URL=https://vllm-public-assets.s3.us-west-2.amazonaws.com/omni-assets/sana-video/v2
- >-
pytest -sv
tests/e2e/online_serving/test_sana_video_expansion.py
tests/e2e/accuracy/sana_video/
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · SenseNova-U1 · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/offline_inference/test_sensenova_u1_expansion.py
tests/e2e/offline_inference/test_sensenova_u1_text2img_expansion.py
tests/e2e/offline_inference/test_sensenova_u1_img2img_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · MammothModa2 · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/offline_inference/test_mammoth_moda2_expansion.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: "Diffusion · Helios · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/accuracy/test_video_streaming_output_similarity.py
-m "slow and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
# Split the old shared H100 2-GPU sweep: one pytest process collected every
# slow+cards_2 diffusion file and exceeded 90 minutes.
- label: "Diffusion · Qwen-Image · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_qwen_image_edit_expansion.py
tests/e2e/online_serving/test_qwen_image_layered_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · Wan2.1 VACE · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_wan_2_1_vace_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · LongCat · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_longcat_image_expansion.py
tests/e2e/online_serving/test_longcat_image_edit_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · Bagel · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_bagel_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · Boogu · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_boogu_image_expansion.py
tests/e2e/online_serving/test_boogu_image_edit_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · Flux · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_flux_2_dev_expansion.py
tests/e2e/offline_inference/test_flux1_kontext_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · GLM-Image · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_glm_image_expansion.py
tests/e2e/offline_inference/test_glm_image_autoround_w4a16_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · LTX · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_ltx.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · Krea2 · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/offline_inference/test_krea2_expansion.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · DreamZero · H100 · 2-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_dreamzero_expansion.py
tests/e2e/accuracy/test_dreamzero.py
-m "slow and diffusion and H100 and cards_2"
--run-level "full_model"
mirror_hardwares: h100_2
- label: "Diffusion · H100 · 3-GPU"
timeout_in_minutes: 120
commands:
- >-
pytest -sv
tests/e2e/ -m "slow and diffusion and H100 and cards_3"
--run-level "full_model"
mirror_hardwares: h100_3
- 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"
--ignore=tests/e2e/online_serving/test_magi2.py
mirror_hardwares: h100_4
# Dedicated: HiDream-O1 accuracy needs a long TP2 run; the shared H100
# 2-GPU sweep is only 90 minutes.
- label: "Diffusion · HiDream-O1-Image Accuracy · H100 · 2-GPU"
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/accuracy/test_hidream_o1_image.py -m "slow and diffusion and cuda and H100 and cards_2" --run-level "full_model"
mirror_hardwares: h100_2
# Dedicated: Boogu CFG-parallel size 3 needs 3 GPUs; weekly has no H100 3-GPU sweep.
- label: "Diffusion · Boogu Edit CFG · H100 · 3-GPU"
timeout_in_minutes: 120
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_boogu_image_edit_expansion.py
-k "test_double_guidance_cfg_parallel and cfg_parallel_3_full"
-m "slow and diffusion and cuda and H100 and cards_3"
--run-level "full_model"
mirror_hardwares: h100_3
# Dedicated: MAGI-2 Preview serving smoke needs ~30 min server init; the
# shared H100 4-GPU sweep is only 90 minutes.
- label: "Diffusion · MAGI-2 Preview Serving Smoke · H100 · 4-GPU"
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/online_serving/test_magi2.py -m "slow and diffusion and cuda and H100 and cards_4" --run-level "full_model"
mirror_hardwares: h100_4
Reference in new issue View Git Blame Copy Permalink