anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
765caa2a121aec024201936c4decb1151225991c
vllm-omni/.buildkite/npu/test-npu-nightly.yml
T
zzh e0c2b9d73f Adapt HunyuanImage3.0 test for npu (#5436) 
Signed-off-by: zzh <943967662@qq.com>
2026-08-03 06:31:50 +00:00

206 lines
9.1 KiB
YAML
Raw Blame History

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"
steps:
- label: ":full_moon: Omni · Perf Test · No Async Chunk"
key: nightly-omni-performance-no-async-chunk
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
commands:
- export BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
exit $$EXIT
- label: ":full_moon: Omni · Perf Test · Async Chunk"
key: nightly-omni-performance-async-chunk
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
commands:
- export BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
exit $$EXIT
- label: ":robot: Omni · MiniCPM-o 4.5 Test"
mirror_hardwares: a3_npu_2
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
commands:
- pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5_expansion.py -m 'full_model' --run-level 'full_model'
- group: ":card_index_dividers: TTS Model Test"
key: nightly-tts-test-group
depends_on: upload-nightly-pipeline
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
steps:
- label: ":full_moon: TTS · Perf Test"
timeout_in_minutes: 180
mirror_hardwares: a3_npu_2
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
commands:
- export BENCHMARK_DIR=tests/dfx/perf/results
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_tts.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
exit $$EXIT
- group: ":card_index_dividers: Diffusion X2I(&A&T) Model Test"
key: nightly-diffusion-x2iat-group
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"
steps:
- label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image-Edit-2511"
key: nightly-diffusion-x2iat-performance-qwen-image-edit-2511
timeout_in_minutes: 180
mirror_hardwares: a3_npu_8
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- export CACHE_DIT_VERSION=1.3.0
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen_image_edit_2511_vllm_omni.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- group: ":card_index_dividers: Diffusion I2I Model Test"
key: nightly-HunyuanImage3-x2i-test-group
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"
steps:
- label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HUNYUAN_IMAGE3_MODEL: "tencent/HunyuanImage-3.0-Instruct"
HUNYUAN_IMAGE3_DEVICES: "0,1,2,3"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- pytest -s -v tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py -m "full_model and A3" --run-level full_model
- group: ":card_index_dividers: Diffusion Benchmark Perf Test"
key: nightly-diffusion-benchmark-group
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"
steps:
- label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 CFGP=2"
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_cfgp2.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 SP=2"
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_sp2.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=4"
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp4.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- group: ":card_index_dividers: Diffusion X2V Model Test"
key: nightly-diffusion-x2v-group
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"
steps:
- label: ":full_moon: Diffusion X2V · Function Test"
mirror_hardwares: a2b3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
commands:
- pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k npu_i2v --run-level "full_model"
- label: ":full_moon: Diffusion X2V · Perf Test"
key: nightly-diffusion-x2v-performance
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
Reference in new issue View Git Blame Copy Permalink