85 lines
3.6 KiB
YAML
85 lines
3.6 KiB
YAML
# AMD MI300 `full_model` nightly coverage during burn-in.
|
|
# All jobs are non-blocking until the lane has stable runtime evidence.
|
|
# Historical build #11646 was red in Function Expansion and Accuracy (one
|
|
# async_chunk similarity mismatch; Seed-TTS WER 0.376480 > 0.35).
|
|
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
HF_HUB_DOWNLOAD_TIMEOUT: 300
|
|
HF_HUB_ETAG_TIMEOUT: 60
|
|
|
|
steps:
|
|
# MI325 is the repository's legacy ROCm pytest marker. The AMD template maps
|
|
# agent_pool to the current MI300 Buildkite queues independently of that mark.
|
|
- group: ":full_moon: Qwen3-Omni MI300 Nightly"
|
|
steps:
|
|
- label: "Qwen3-Omni Function Expansion"
|
|
agent_pool: mi300_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: NonBlocking
|
|
timeout_in_minutes: 180
|
|
commands:
|
|
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
|
|
- pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
|
|
|
|
- label: "Qwen3-Omni Accuracy"
|
|
agent_pool: mi300_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: NonBlocking
|
|
timeout_in_minutes: 180
|
|
artifact_paths:
|
|
- tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json
|
|
commands:
|
|
- export SEED_TTS_WER_EVAL=1
|
|
# PyTorch ROCm uses the torch.cuda device namespace.
|
|
- export SEED_TTS_EVAL_DEVICE=cuda:1
|
|
- pytest -s -v tests/e2e/accuracy/qwen3_omni/test_qwen3_omni.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
|
|
# Native tests run from the image copy under /app/vllm-omni, while
|
|
# Buildkite's artifact hook searches the checkout workspace.
|
|
- |
|
|
if [[ "$$PWD" != "$${BUILDKITE_BUILD_CHECKOUT_PATH:?}" ]]; then
|
|
artifact_dir="$${BUILDKITE_BUILD_CHECKOUT_PATH}/tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc"
|
|
mkdir -p "$$artifact_dir"
|
|
cp -v tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json "$$artifact_dir/"
|
|
fi
|
|
|
|
- label: "Qwen3-Omni Documentation Examples"
|
|
agent_pool: mi300_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: NonBlocking
|
|
timeout_in_minutes: 120
|
|
commands:
|
|
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
|
|
- pytest -s -v tests/examples/online_serving/test_qwen3_omni.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
|
|
|
|
- label: "Qwen3-Omni AITER-on Smoke"
|
|
agent_pool: mi300_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: NonBlocking
|
|
timeout_in_minutes: 90
|
|
commands:
|
|
- export VLLM_ROCM_USE_AITER=1
|
|
- pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py::test_text_to_text_audio_001 -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
|
|
|
|
- group: ":speaker: CosyVoice3 MI300 Nightly"
|
|
steps:
|
|
# Exercise all sync/async and Chinese/English cases with the platform's
|
|
# default attention backend. On ROCm this retains end-to-end AITER
|
|
# coverage without putting its cold JIT build on the READY critical path.
|
|
- label: "CosyVoice3-TTS E2E Test"
|
|
agent_pool: mi300_1
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: NonBlocking
|
|
timeout_in_minutes: 90
|
|
retry:
|
|
automatic:
|
|
- exit_status: 134
|
|
limit: 1
|
|
commands:
|
|
- pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts_expansion.py -m "slow" --run-level "core_model"
|