anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI/Build] Diff-aware source_file_dependencies for CUDA/NPU pipelines (#6597)

Browse Source 
Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
wangyuandCursor authored and GitHub committed 2026-09-10 01:40:01 -07:00
1 parent a7c295d544
commit 5b927b7ceb
25 files changed
+1479 -411
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/cuda/bootstrap-upload-steps.yml
+21 -7
View File
@@ -22,34 +22,48 @@ steps:
agents:
queue: "cpu_queue_premerge"
# L3 Test — PR merge-test label (diff-aware) or main+WEEKLY=1 (--e2e, full E2E group)
# L3 Test — PR merge-test label (diff-aware) or main (full pipeline / WEEKLY --e2e)
- label: "Upload Merge Pipeline"
depends_on: image-build
key: upload-merge-pipeline
commands:
- |
EXTRA=""
if [ "${WEEKLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
EXTRA="--e2e"
if [ "${BUILDKITE_BRANCH}" = "main" ]; then
if [ "${WEEKLY:-}" = "1" ]; then
EXTRA="--e2e"
else
EXTRA="--all"
fi
fi
python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-merge.yml
agents:
queue: "cpu_queue_premerge"
# L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
# L4 Test — main+NIGHTLY=1 (full pipeline), or PR nightly-test label (diff-aware)
- label: "Upload Nightly Pipeline"
depends_on: image-build
key: upload-nightly-pipeline
commands:
- python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/cuda/test-nightly.yml
- |
EXTRA=""
if [ "${NIGHTLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
EXTRA="--all"
fi
python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-nightly.yml
agents:
queue: "cpu_queue_premerge"
# L5 Test — main+WEEKLY=1 / NON_CRITICAL=1 (scheduled), or PR with weekly-test label
# L5 Test — main+WEEKLY=1 / NON_CRITICAL=1 (full pipeline), or PR weekly-test label (diff-aware)
- label: "Upload Weekly Pipeline"
depends_on: image-build
key: upload-weekly-pipeline
commands:
- python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/cuda/test-weekly.yml
- |
EXTRA=""
if [ "${BUILDKITE_BRANCH}" = "main" ]; then
EXTRA="--all"
fi
python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-weekly.yml
agents:
queue: "cpu_queue_premerge"
.buildkite/cuda/test-merge.yml
+9 -120
View File
@@ -78,21 +78,7 @@ steps:
depends_on: upload-merge-pipeline
steps:
- label: "TTS · Qwen3-TTS CustomVoice Test"
source_file_dependencies:
- tests/e2e/features/prefill_phase/
- vllm_omni/worker/gpu_model_runner.py
- tests/helpers/media.py
- tests/e2e/online_serving/test_qwen3_tts_customvoice.py
- tests/e2e/offline_inference/test_qwen3_tts_customvoice.py
- vllm_omni/model_executor/models/qwen3_tts/
- vllm_omni/model_executor/models/common/qwen3_code_predictor.py
- vllm_omni/model_executor/models/common/snake_activation.py
- vllm_omni/model_executor/models/common/alias_free_activation.py
- vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
- vllm_omni/deploy/qwen3_tts.yaml
- vllm_omni/entrypoints/openai/serving_speech.py
- vllm_omni/entrypoints/openai/tts_adapters/
- vllm_omni/engine/stage_pool.py
source_file_dependencies: tts_qwen3_tts_function
commands:
- |
timeout 40m bash -c "
@@ -103,21 +89,7 @@ steps:
mirror_hardwares: l4_1
- label: "TTS · Qwen3-TTS Base Test"
source_file_dependencies:
- tests/helpers/media.py
- tests/e2e/online_serving/test_qwen3_tts_base.py
- tests/e2e/offline_inference/test_qwen3_tts_base.py
- vllm_omni/model_executor/models/qwen3_tts/
- vllm_omni/model_executor/models/common/qwen3_code_predictor.py
- vllm_omni/model_executor/models/common/snake_activation.py
- vllm_omni/model_executor/models/common/alias_free_activation.py
- vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
- vllm_omni/deploy/qwen3_tts.yaml
- vllm_omni/entrypoints/openai/serving_speech.py
- vllm_omni/entrypoints/openai/tts_adapters/
- vllm_omni/engine/stage_pool.py
- .buildkite/common/scripts/run_cov_split.sh
- pyproject.toml
source_file_dependencies: tts_qwen3_tts_cov
# 40 -> 60: the coverage split runs the model twice.
timeout_in_minutes: 60
commands:
@@ -132,36 +104,14 @@ steps:
mirror_hardwares: l4_1
- label: "Omni · Qwen3-Omni Test"
source_file_dependencies:
- tests/e2e/offline_inference/test_qwen3_omni.py
- tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py
- tests/e2e/online_serving/test_qwen3_omni.py
- tests/helpers/runtime.py
- vllm_omni/entrypoints/openai/serving_chat.py
- vllm_omni/model_executor/models/qwen3_omni/
- vllm_omni/model_executor/models/common/qwen3_code_predictor.py
- vllm_omni/model_executor/models/common/snake_activation.py
- vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py
- vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
- vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
- vllm_omni/deploy/qwen3_omni_moe.yaml
- vllm_omni/deploy/qwen3_omni_moe_thinking.yaml
source_file_dependencies: omni_qwen3_omni_function
timeout_in_minutes: 50
commands:
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py -m 'advanced_model and cuda' --run-level 'advanced_model'
mirror_hardwares: h100_2
- label: "Omni · MiniCPM-o 4.5 Test"
source_file_dependencies:
- tests/e2e/offline_inference/test_minicpmo_4_5.py
- tests/e2e/online_serving/test_minicpmo_4_5.py
- vllm_omni/transformers_utils/chat_templates/minicpmo45_native.jinja
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/models/step_audio2/
- vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
- vllm_omni/model_executor/models/cosyvoice3/utils.py
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
- vllm_omni/deploy/minicpmo_4_5.yaml
source_file_dependencies: omni_minicpmo_4_5_function
timeout_in_minutes: 50
commands:
- pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'advanced_model and cuda' --run-level 'advanced_model'
@@ -174,59 +124,14 @@ steps:
mirror_hardwares: h100_2
- label: "Omni · MiniCPM-o 4.5 Duplex Test"
source_file_dependencies:
- tests/assets/minicpmo_4_5/response_required_16k.wav
- tests/assets/minicpmo_4_5/soft_interrupt_16k.wav
- tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
- tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
- tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
- tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_server_vad.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
- vllm_omni/deploy/minicpmo_4_5.yaml
- tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
- vllm_omni/engine/duplex/
- vllm_omni/entrypoints/duplex/
# Public duplex client library + its unit suites: client-side
# changes must re-run the duplex e2e group. The live client probe
# (test_duplex_client_live.py, single GPU, core tier) runs in the
# ready pipeline's duplex group.
- vllm_omni/clients/
- tests/clients/
- vllm_omni/entrypoints/duplex_request_client.py
- vllm_omni/outputs/duplex.py
- vllm_omni/model_executor/duplex_sampling.py
- tests/engine/duplex/
- tests/entrypoints/duplex/
- tests/model_executor/models/minicpmo_4_5/duplex/
# Legacy Realtime probe client + video stacking used by the e2e drivers.
- vllm_omni/experimental/fullduplex/
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/models/step_audio2/
- vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
- vllm_omni/model_executor/models/cosyvoice3/utils.py
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
- vllm_omni/core/sched/
- vllm_omni/outputs/multimodal_accumulation.py
- vllm_omni/engine/stage_init_utils.py
- vllm_omni/engine/async_omni_engine.py
- vllm_omni/engine/orchestrator.py
- vllm_omni/entrypoints/cli/serve.py
- vllm_omni/entrypoints/openai/api_server.py
- vllm_omni/entrypoints/openai/duplex_capability.py
- vllm_omni/config/stage_config.py
source_file_dependencies: omni_minicpmo_4_5_duplex_function
timeout_in_minutes: 50
commands:
- pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'advanced_model and cuda' --run-level 'advanced_model'
mirror_hardwares: h100_1
- label: "Diffusion · Qwen Image Test"
source_file_dependencies:
- tests/e2e/online_serving/test_qwen_image.py
- vllm_omni/diffusion/models/qwen_image/
- vllm_omni/diffusion/models/dmd2/
- vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py
source_file_dependencies: diffusion_qwen_image_function
commands:
- |
timeout 40m bash -c '
@@ -236,11 +141,7 @@ steps:
mirror_hardwares: h100_1
- label: "Diffusion · Wan22 Test"
source_file_dependencies:
- tests/e2e/offline_inference/test_wan22_t2v.py
- tests/e2e/online_serving/test_wan22_t2v.py
- vllm_omni/diffusion/models/wan2_2/
- vllm_omni/diffusion/models/dmd2/
source_file_dependencies: diffusion_wan22_function
commands:
- |
timeout 40m bash -c "
@@ -250,9 +151,7 @@ steps:
mirror_hardwares: h100_1
- label: "Diffusion · HunyuanVideo-1.5 Test"
source_file_dependencies:
- tests/e2e/online_serving/test_hunyuan_video_15_expansion.py
- vllm_omni/diffusion/models/hunyuan_video/
source_file_dependencies: diffusion_hunyuan_video_function
commands:
- |
timeout 40m bash -c "
@@ -262,17 +161,7 @@ steps:
mirror_hardwares: h100_1
- label: "Diffusion · MiniMax-H3 L3 DLO DP2 and FastH3"
source_file_dependencies:
- tests/e2e/online_serving/minimax_h3/
- tests/helpers/assertions.py
- tests/helpers/mark.py
- tests/helpers/media.py
- tests/helpers/runtime.py
- vllm_omni/diffusion/models/minimax_h3/
- vllm_omni/diffusion/lora/
- vllm_omni/diffusion/offloader/
- vllm_omni/diffusion/distributed/
- vllm_omni/entrypoints/openai/
source_file_dependencies: diffusion_minimax_h3_function
# Keep four server lifecycles in one Buildkite job, but never in one
# pytest process. DLO uses multiprocessing shared-memory queues; the
# parent's resource_tracker can retain a stale /psm_* entry during
.buildkite/cuda/test-nightly.yml
+75 -29
View File
@@ -12,26 +12,34 @@ steps:
- group: ":card_index_dividers: Omni Model Test"
key: nightly-omni-test-group
depends_on: upload-nightly-pipeline
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "omni-test"
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Omni · Function Test with H100 · Single-GPU"
source_file_dependencies:
- omni_qwen3_omni_function
- omni_minicpmo_4_5_function
timeout_in_minutes: 120
commands:
- pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and B200 and omni and cards_1" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
- label: ":full_moon: Omni · Function Test with H100 · 2-GPU"
source_file_dependencies:
- omni_qwen3_omni_function
- omni_minicpmo_4_5_function
timeout_in_minutes: 90
commands:
- pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and B200 and omni and cards_2" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py
- label: ":full_moon: Omni · MiniCPM-o 4.5 Duplex Test"
source_file_dependencies: omni_minicpmo_4_5_duplex_function
timeout_in_minutes: 50
commands:
- pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py -m "full_model and cuda and H100 and omni and cards_1" --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Omni · Doc Test with L4 · 4-GPU"
source_file_dependencies: omni_qwen2_5_omni_doc
timeout_in_minutes: 90
commands:
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
@@ -39,12 +47,14 @@ steps:
mirror_hardwares: l4_4
- label: ":full_moon: Omni · Doc Test with H100 · 2-GPU"
source_file_dependencies: omni_qwen3_omni_doc
timeout_in_minutes: 90
commands:
- pytest -s -v tests/examples/ -m "full_model and omni and H100 and cards_2" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Omni · Accuracy Test"
source_file_dependencies: omni_qwen3_omni_accuracy
timeout_in_minutes: 180
commands:
- export SEED_TTS_WER_EVAL=1
@@ -58,6 +68,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
source_file_dependencies: omni_minicpmo_4_5_accuracy
timeout_in_minutes: 180
commands:
- export SEED_TTS_WER_EVAL=1
@@ -71,6 +82,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Omni · Perf Test · No Async Chunk"
source_file_dependencies: omni_qwen3_omni_perf
key: nightly-omni-performance-no-async-chunk
timeout_in_minutes: 300
commands:
@@ -84,6 +96,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Omni · Perf Test · Async Chunk"
source_file_dependencies: omni_qwen3_omni_perf
key: nightly-omni-performance-async-chunk
timeout_in_minutes: 180
commands:
@@ -97,19 +110,21 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test"
source_file_dependencies: omni_minicpmo_4_5_perf
key: nightly-omni-performance-minicpmo-4-5
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_minicpmo_4_5.json
pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5.json -m "H100 and cards_1"
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
exit $$EXIT
mirror_hardwares: h100_1
- label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Seed-TTS Perf Test"
source_file_dependencies: omni_minicpmo_4_5_duplex_perf
key: nightly-omni-performance-minicpmo-4-5-duplex-seed-tts
timeout_in_minutes: 180
commands:
@@ -123,6 +138,7 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: Omni · Multi-Replica Startup Test with 4x H100"
source_file_dependencies: omni_qwen3_omni_function
timeout_in_minutes: 45
commands:
- pytest -s -v tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py -m "full_model" --run-level "core_model"
@@ -131,10 +147,11 @@ steps:
- group: ":card_index_dividers: TTS Model Test"
key: nightly-tts-test-group
depends_on: upload-nightly-pipeline
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: TTS · Function Test with L4"
source_file_dependencies: tts_qwen3_tts_function
timeout_in_minutes: 120
commands:
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
@@ -144,6 +161,7 @@ steps:
mirror_hardwares: l4_1
- label: ":full_moon: TTS · Perf Test · Single-GPU"
source_file_dependencies: tts_qwen3_tts_perf
key: nightly-tts-performance-single
timeout_in_minutes: 180
commands:
@@ -158,6 +176,7 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: TTS · Perf Test · 2-GPU"
source_file_dependencies: tts_qwen3_tts_perf
key: nightly-tts-performance-2gpu
timeout_in_minutes: 180
commands:
@@ -180,6 +199,7 @@ steps:
steps:
- label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 2-GPU"
source_file_dependencies: diffusion_tiny_model
timeout_in_minutes: 30
# NOTE: Single-GPU (core_model) tiny model tests run on the ready label,
# so nightly only adds the multi-GPU parallelism configurations.
@@ -193,6 +213,7 @@ steps:
mirror_hardwares: l4_2
- label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 4-GPU"
source_file_dependencies: diffusion_tiny_model
timeout_in_minutes: 30
# CFG+TP extra_test_groups request 2×2=4 devices (see get_required_device_count).
commands:
@@ -204,11 +225,11 @@ steps:
depends_on: upload-nightly-pipeline
if: >-
build.env("NIGHTLY") == "1" ||
build.pull_request.labels includes "nightly-test" ||
build.pull_request.labels includes "diffusion-x2iat-test"
build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Single-GPU"
source_file_dependencies: diffusion_qwen_image_function
timeout_in_minutes: 120
commands:
- >-
@@ -219,6 +240,7 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · 2-GPU"
source_file_dependencies: diffusion_qwen_image_function
timeout_in_minutes: 120
commands:
- >-
@@ -228,30 +250,26 @@ steps:
--run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2I(&A&T) · Boogu Edit CFG · 3-GPU"
- label: ":full_moon: Diffusion X2I(&A&T) · Z-Image Function Test · L4 · 4-GPU"
source_file_dependencies: diffusion_z_image_function
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"
tests/e2e/online_serving/test_zimage_expansion.py
-m "full_model and diffusion and L4 and cards_4"
--run-level "full_model"
mirror_hardwares: h100_3
- label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4 · 4-GPU"
timeout_in_minutes: 120
commands:
- pytest -sv tests/e2e/ -k "not test_wan and not hunyuan" -m "full_model and diffusion and L4 and cards_4" --run-level "full_model" --ignore=tests/e2e/accuracy
mirror_hardwares: l4_4
- label: ":full_moon: Diffusion X2I(&A&T) · Doc Test"
source_file_dependencies: diffusion_text_to_image_doc
timeout_in_minutes: 60
commands:
- pytest -s -v tests/examples/*/test_text_to_image.py -m "full_model and example and H100" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2I(&A&T) · Accuracy Test"
source_file_dependencies: diffusion_qwen_image_accuracy
timeout_in_minutes: 180
commands:
- export VLLM_HTTP_TIMEOUT_KEEP_ALIVE=120
@@ -260,6 +278,7 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
source_file_dependencies: diffusion_hunyuan_image3_accuracy
timeout_in_minutes: 180
commands:
- export HUNYUAN_IMAGE3_MODEL="tencent/HunyuanImage-3.0-Instruct"
@@ -267,13 +286,8 @@ steps:
- pytest -s -v tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py -m full_model --run-level full_model
mirror_hardwares: h100_4
- label: ":full_moon: HiDream-O1-Image · Accuracy Test"
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/accuracy/test_hidream_o1_image.py -m full_model --run-level full_model
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · Single-GPU"
source_file_dependencies: diffusion_qwen_image_perf
key: nightly-diffusion-x2iat-performance-qwen-image-single
timeout_in_minutes: 180
commands:
@@ -289,6 +303,7 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · 4-GPU"
source_file_dependencies: diffusion_qwen_image_perf
key: nightly-diffusion-x2iat-performance-qwen-image-4gpu
timeout_in_minutes: 180
commands:
@@ -309,59 +324,73 @@ steps:
depends_on: upload-nightly-pipeline
if: >-
build.env("NIGHTLY") == "1" ||
build.pull_request.labels includes "nightly-test" ||
build.pull_request.labels includes "diffusion-x2v-test"
build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test · Single-GPU"
source_file_dependencies: diffusion_wan22_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda and H100 and cards_1" --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test · 2-GPU"
source_file_dependencies: diffusion_wan22_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda and H100 and cards_2" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test · Single-GPU"
source_file_dependencies: diffusion_wan22_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda and H100 and cards_1" --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test · 2-GPU"
source_file_dependencies: diffusion_wan22_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda and H100 and cards_2" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · HunyuanVideo-1.5 Function Test"
source_file_dependencies: diffusion_hunyuan_video_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/online_serving/test_hunyuan_video_15_expansion.py -m "full_model and cuda" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · MAGI-2 Preview Serving Smoke"
timeout_in_minutes: 180
- label: ":full_moon: Diffusion X2V · LingBot Function Test"
source_file_dependencies: diffusion_lingbot_function
timeout_in_minutes: 120
commands:
- pytest -s -v tests/e2e/online_serving/test_magi2.py -m "advanced_model and diffusion and cuda and H100 and cards_4" --run-level "advanced_model"
mirror_hardwares: h100_4
- >-
pytest -s -v
tests/e2e/online_serving/test_lingbot_video.py
tests/e2e/online_serving/test_lingbot_video_moe.py
tests/e2e/offline_inference/test_lingbot_world_v2.py
-m "full_model and diffusion and H100 and cards_1"
--run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2V · Doc Test"
source_file_dependencies: diffusion_image_to_video_doc
timeout_in_minutes: 60
commands:
- pytest -s -v tests/examples/offline_inference/test_image_to_video.py -m "full_model and example and H100" --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2V · Other Function Test"
- label: ":full_moon: Diffusion X2V · Wan2.2 Autoround Function Test"
source_file_dependencies: diffusion_wan22_function
timeout_in_minutes: 90
commands:
- pytest -s -v tests/e2e/offline_inference/test_wan22_autoround_w4a16_expansion.py -m "full_model and cuda" --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · Wan2.2 Accuracy Test"
source_file_dependencies: diffusion_wan22_accuracy
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/accuracy/wan22_i2v/test_wan22_i2v_video_similarity.py -m full_model --run-level full_model
@@ -369,12 +398,14 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · MiniMax H3 I2VA/Ref2VA Accuracy Test"
source_file_dependencies: diffusion_minimax_h3_accuracy
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/accuracy/minimax_h3/test_minimax_h3_i2va_ref2va_similarity.py -m full_model --run-level full_model
mirror_hardwares: h100_4
- label: ":full_moon: Diffusion X2V · Other Accuracy Test"
- label: ":full_moon: Diffusion X2V · HunyuanVideo-1.5 Accuracy Test"
source_file_dependencies: diffusion_hunyuan_video_accuracy
timeout_in_minutes: 180
commands:
- pytest -s -v tests/e2e/accuracy/hunyuanvideo15_t2v/test_hunyuanvideo15_t2v_video_similarity.py -m full_model --run-level full_model
@@ -382,6 +413,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · Perf Test · Single-GPU"
source_file_dependencies: diffusion_wan22_perf
key: nightly-diffusion-x2v-performance-single
timeout_in_minutes: 180
commands:
@@ -396,6 +428,9 @@ steps:
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion X2V · Perf Test · 2-GPU"
source_file_dependencies:
- diffusion_wan22_perf
- diffusion_cosmos3_perf
key: nightly-diffusion-x2v-performance-2gpu
timeout_in_minutes: 180
commands:
@@ -414,6 +449,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · Perf Test · HunyuanVideo-1.5"
source_file_dependencies: diffusion_hunyuan_video_perf
key: nightly-diffusion-x2v-performance-hunyuanvideo15
timeout_in_minutes: 180
commands:
@@ -431,6 +467,7 @@ steps:
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2V · Perf Test · MiniMax-H3"
source_file_dependencies: diffusion_minimax_h3_perf
key: nightly-diffusion-x2v-performance-minimax-h3
timeout_in_minutes: 180
commands:
@@ -450,54 +487,63 @@ steps:
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Diffusion · Distributed Test with L4 · 2-GPU"
source_file_dependencies: diffusion_distributed_attention
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_2' --run-level "full_model"
mirror_hardwares: l4_2
- label: ":full_moon: Diffusion · Distributed Test with L4 · 3-GPU"
source_file_dependencies: diffusion_distributed_attention
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_3' --run-level "full_model"
mirror_hardwares: l4_3
- label: ":full_moon: Diffusion · Distributed Test with L4 · 4-GPU"
source_file_dependencies: diffusion_distributed_attention
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_4' --run-level "full_model"
mirror_hardwares: l4_4
- label: ":full_moon: Diffusion · Distributed Test with H100 · 2-GPU"
source_file_dependencies: diffusion_distributed_attention
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and H100 and cards_2' --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion · Distributed Test with H100 · 4-GPU"
source_file_dependencies: diffusion_distributed_attention
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and H100 and cards_4' --run-level "full_model"
mirror_hardwares: h100_4
- label: ":full_moon: Diffusion · Offloader Test"
source_file_dependencies: diffusion_offloader
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/offloader -m "full_model and cuda"
mirror_hardwares: l4_1
- label: ":full_moon: Diffusion · Quantization Test with H100 · Single-GPU"
source_file_dependencies: diffusion_quantization
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/quantization -m 'full_model and cuda and H100' --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Diffusion · MiniMax H3 FP8 Quality Test with H100 · 2-GPU"
source_file_dependencies: diffusion_minimax_h3_function
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py -m 'full_model and cuda and H100' --run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion · Quantization Test with L4"
source_file_dependencies: diffusion_quantization
timeout_in_minutes: 60
commands:
- pip install "vllm-gguf-plugin==0.0.4"
.buildkite/cuda/test-ready.yml
+16 -130
View File
@@ -54,16 +54,19 @@ steps:
mirror_hardwares: l4_1
- label: "Diffusion · Distributed Test · Single-GPU"
source_file_dependencies: diffusion_distributed_attention
commands:
- timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_1' --run-level "core_model"
mirror_hardwares: l4_1
- label: "Diffusion · Distributed Test · 2-GPU"
source_file_dependencies: diffusion_distributed_attention
commands:
- timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_2' --run-level "core_model"
mirror_hardwares: l4_2
- label: "Diffusion · Distributed & Attention Test · 4-GPU"
source_file_dependencies: diffusion_distributed_attention
commands:
- timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_4' --run-level "core_model"
- timeout 20m pytest -sv tests/diffusion/attention/test_attention_sp.py -m 'core_model and cuda and L4 and cards_4' --run-level "core_model"
@@ -120,29 +123,14 @@ steps:
depends_on: upload-ready-pipeline
steps:
- label: "Custom Pipeline Test"
source_file_dependencies:
- tests/e2e/features/custom_pipeline/
- tests/e2e/features/helpers/custom_pipeline.py
- vllm_omni/diffusion/
- vllm_omni/engine/
- vllm_omni/entrypoints/
- vllm_omni/inputs/
- vllm_omni/outputs/
source_file_dependencies: custom_pipeline
commands:
- timeout 20m pytest -s -v tests/e2e/features/custom_pipeline/ -m "core_model"
mirror_hardwares: l4_1
- label: "RLHF · VeRL-Omni E2E Test"
source_file_dependencies:
- tests/e2e/features/rlhf_test/test_verl_omni_e2e.py
- tests/e2e/features/helpers/verl_omni_server.py
- tests/e2e/features/helpers/custom_pipeline.py
- vllm_omni/diffusion/
- vllm_omni/engine/
- vllm_omni/entrypoints/
- vllm_omni/inputs/
- vllm_omni/outputs/
source_file_dependencies: rlhf_verl_omni
commands:
- |
timeout 20m bash -c "
@@ -151,17 +139,7 @@ steps:
mirror_hardwares: l4_1
- label: "Omni · Qwen3-Omni Test"
source_file_dependencies:
- tests/e2e/online_serving/test_qwen3_omni.py
- tests/helpers/runtime.py
- vllm_omni/entrypoints/openai/serving_chat.py
- vllm_omni/model_executor/models/qwen3_omni/
- vllm_omni/model_executor/models/common/qwen3_code_predictor.py
- vllm_omni/model_executor/models/common/snake_activation.py
- vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py
- vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
- vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
- vllm_omni/deploy/qwen3_omni_moe.yaml
source_file_dependencies: omni_qwen3_omni_function
commands:
- |
timeout 20m bash -c "
@@ -170,14 +148,7 @@ steps:
mirror_hardwares: h100_2
- label: "Omni · MiniCPM-o 4.5 Offline Test"
source_file_dependencies:
- tests/e2e/offline_inference/test_minicpmo_4_5.py
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/models/step_audio2/
- vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
- vllm_omni/model_executor/models/cosyvoice3/utils.py
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
- vllm_omni/deploy/minicpmo_4_5.yaml
source_file_dependencies: omni_minicpmo_4_5_function
commands:
- |
timeout 20m bash -c "
@@ -186,15 +157,7 @@ steps:
mirror_hardwares: h100_1
- label: "Omni · MiniCPM-o 4.5 Online Test"
source_file_dependencies:
- tests/e2e/online_serving/test_minicpmo_4_5.py
- vllm_omni/transformers_utils/chat_templates/minicpmo45_native.jinja
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/models/step_audio2/
- vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
- vllm_omni/model_executor/models/cosyvoice3/utils.py
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
- vllm_omni/deploy/minicpmo_4_5.yaml
source_file_dependencies: omni_minicpmo_4_5_function
commands:
- |
timeout 20m bash -c "
@@ -203,48 +166,7 @@ steps:
mirror_hardwares: h100_1
- label: "Omni · MiniCPM-o 4.5 Duplex Test"
source_file_dependencies:
- tests/assets/minicpmo_4_5/response_required_16k.wav
- tests/assets/minicpmo_4_5/soft_interrupt_16k.wav
- tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
- tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
- tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
- tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_server_vad.py
- tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
- vllm_omni/deploy/minicpmo_4_5.yaml
- tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
- vllm_omni/engine/duplex/
- vllm_omni/entrypoints/duplex/
# Public duplex client library + its unit suites: client-side
# changes must re-run the duplex e2e group, which includes the
# live client probe (test_duplex_client_live.py, single GPU).
- vllm_omni/clients/
- tests/clients/
- tests/e2e/online_serving/test_duplex_client_live.py
- vllm_omni/entrypoints/duplex_request_client.py
- vllm_omni/outputs/duplex.py
- vllm_omni/model_executor/duplex_sampling.py
- tests/engine/duplex/
- tests/entrypoints/duplex/
- tests/model_executor/models/minicpmo_4_5/duplex/
# Legacy Realtime probe client + video stacking used by the e2e drivers.
- vllm_omni/experimental/fullduplex/
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/models/step_audio2/
- vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
- vllm_omni/model_executor/models/cosyvoice3/utils.py
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
- vllm_omni/core/sched/
- vllm_omni/outputs/multimodal_accumulation.py
- vllm_omni/engine/stage_init_utils.py
- vllm_omni/engine/async_omni_engine.py
- vllm_omni/engine/orchestrator.py
- vllm_omni/entrypoints/cli/serve.py
- vllm_omni/entrypoints/openai/api_server.py
- vllm_omni/entrypoints/openai/duplex_capability.py
- vllm_omni/config/stage_config.py
source_file_dependencies: omni_minicpmo_4_5_duplex_function
commands:
- |
timeout 35m bash -c "
@@ -254,29 +176,14 @@ steps:
- label: "Omni · MiniCPM-o 4.5 Perf Test"
timeout_in_minutes: 60
source_file_dependencies:
- tests/dfx/perf/tests/test_minicpmo_4_5_ready.json
- vllm_omni/deploy/minicpmo_4_5.yaml
- vllm_omni/model_executor/models/minicpmo_4_5/
- vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
source_file_dependencies: omni_minicpmo_4_5_perf
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 cuda'
mirror_hardwares: h100_1
- label: "TTS · Qwen3-TTS CustomVoice Test"
source_file_dependencies:
- tests/helpers/media.py
- tests/e2e/online_serving/test_qwen3_tts_customvoice.py
- vllm_omni/model_executor/models/qwen3_tts/
- vllm_omni/model_executor/models/common/qwen3_code_predictor.py
- vllm_omni/model_executor/models/common/snake_activation.py
- vllm_omni/model_executor/models/common/alias_free_activation.py
- vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
- vllm_omni/deploy/qwen3_tts.yaml
- vllm_omni/entrypoints/openai/serving_speech.py
- vllm_omni/entrypoints/openai/tts_adapters/
- vllm_omni/engine/stage_pool.py
source_file_dependencies: tts_qwen3_tts_function
commands:
- |
timeout 20m bash -c "
@@ -286,10 +193,7 @@ steps:
mirror_hardwares: l4_1
- label: "Diffusion · Wan22 Test"
source_file_dependencies:
- tests/e2e/online_serving/test_wan22_t2v.py
- vllm_omni/diffusion/models/wan2_2/
- vllm_omni/diffusion/models/dmd2/
source_file_dependencies: diffusion_wan22_function
commands:
- |
timeout 40m bash -c "
@@ -299,12 +203,7 @@ steps:
mirror_hardwares: h100_1
- label: "Diffusion · Cosmos3 Test"
source_file_dependencies:
- tests/e2e/online_serving/test_cosmos3.py
- vllm_omni/diffusion/models/cosmos3/
- vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_wan.py
- vllm_omni/experimental/world_models/
- vllm_omni/model_extras/cosmos3.py
source_file_dependencies: diffusion_cosmos3_function
commands:
- |
timeout 40m bash -c "
@@ -315,14 +214,7 @@ steps:
- label: "Diffusion · MiniMax-H3 DLO DP2 T2VA Test"
timeout_in_minutes: 90
source_file_dependencies:
- tests/e2e/online_serving/test_minimax_h3_dlo_dp2_t2va.py
- tests/helpers/assertions.py
- tests/helpers/runtime.py
- vllm_omni/diffusion/models/minimax_h3/
- vllm_omni/diffusion/offloader/
- vllm_omni/diffusion/distributed/
- vllm_omni/entrypoints/openai/
source_file_dependencies: diffusion_minimax_h3_function
commands:
- |
timeout 80m bash -c "
@@ -332,11 +224,7 @@ steps:
mirror_hardwares: h100_2
- label: "Diffusion · Qwen Image Test"
source_file_dependencies:
- tests/e2e/online_serving/test_qwen_image.py
- vllm_omni/diffusion/models/qwen_image/
- vllm_omni/diffusion/models/dmd2/
- vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py
source_file_dependencies: diffusion_qwen_image_function
commands:
- |
timeout 40m bash -c "
@@ -346,9 +234,7 @@ steps:
mirror_hardwares: h100_1
- label: "Diffusion · HunyuanVideo-1.5 Test"
source_file_dependencies:
- tests/e2e/online_serving/test_hunyuan_video_15_expansion.py
- vllm_omni/diffusion/models/hunyuan_video/
source_file_dependencies: diffusion_hunyuan_video_function
commands:
- |
timeout 40m bash -c "
.buildkite/cuda/test-weekly.yml
+283 -5
View File
@@ -29,36 +29,42 @@ steps:
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"
@@ -70,6 +76,7 @@ steps:
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:
@@ -96,6 +103,7 @@ steps:
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:
@@ -221,21 +229,262 @@ steps:
--run-level "full_model"
mirror_hardwares: l4_4
- label: "Diffusion · H100 · Single-GPU"
timeout_in_minutes: 150
# 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/ -m "slow and diffusion and H100 and cards_1"
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 · H100 · 2-GPU"
- label: "Diffusion · Wan2.1 VACE · H100 · Single-GPU"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/ -m "slow and diffusion and H100 and cards_2"
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"
timeout_in_minutes: 90
commands:
- >-
pytest -sv
tests/e2e/online_serving/test_sana_video_expansion.py
-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
@@ -246,4 +495,33 @@ steps:
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