44 lines
1.9 KiB
YAML
44 lines
1.9 KiB
YAML
steps:
|
|
- group: ":card_index_dividers: Omni Model Test"
|
|
key: ready-omni-group
|
|
depends_on: upload-ready-pipeline
|
|
steps:
|
|
- label: "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: "${HF_TOKEN}"
|
|
commands:
|
|
- pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
|
|
- label: "Omni · MiniCPM-o 4.5 Duplex Test"
|
|
mirror_hardwares: a3_npu_2
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
|
|
HF_TOKEN: "${HF_TOKEN}"
|
|
commands:
|
|
- pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
|
|
- label: "Omni · MiniCPM-o 4.5 Perf Test"
|
|
timeout_in_minutes: 60
|
|
mirror_hardwares: a3_npu_2
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
|
|
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 npu and A3 and omni'
|
|
|
|
# - 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' --run-level 'core_model'
|