35 lines
1.3 KiB
YAML
35 lines
1.3 KiB
YAML
steps:
|
|
- group: ":card_index_dividers: Omni Model Test"
|
|
key: ready-omni-group
|
|
depends_on: upload-ready-pipeline
|
|
steps:
|
|
- label: ":robot: Omni · MiniCPM-o 4.5 Test"
|
|
agents:
|
|
queue: "ascend-a3"
|
|
resource_class: "npu-2"
|
|
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
|
|
plugins:
|
|
- kubernetes:
|
|
podSpecPatch:
|
|
imagePullSecrets:
|
|
- name: swr-secret
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
|
|
HF_TOKEN: "${HF_TOKEN}"
|
|
commands:
|
|
- pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
|
|
|
|
- group: ":card_index_dividers: TTS Model Test"
|
|
key: ready-tts-group
|
|
depends_on: upload-ready-pipeline
|
|
steps:
|
|
- label: ":sound: TTS · Qwen3-TTS CustomVoice Test"
|
|
mirror_hardwares: a2b3_npu_1
|
|
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_qwen3_tts_customvoice.py -m 'core_model and npu' --run-level 'core_model'
|