Follow-up to #2958. MOSS-TTS-Nano was authored before the schema refactor and still shipped as a legacy stage_configs yaml; this aligns it with the same layout the 5 migrated TTS models now use. - vllm_omni/model_executor/models/moss_tts_nano/pipeline.py declares MOSS_TTS_NANO_PIPELINE (single LLM_AR stage, owns_tokenizer, audio output, stop_token_ids=[2] as a hard EOS backstop). - vllm_omni/deploy/moss_tts_nano.yaml holds runtime knobs (max_num_seqs, gpu_memory_utilization, enforce_eager, default_sampling_params, skip_mm_profiling); trust_remote_code stays at deploy top-level. - vllm_omni/config/pipeline_registry.py registers the entry so the lazy registry can resolve it. - moss_tts_nano/__init__.py exports MossTTSNanoForGeneration (VoxCPM2 pattern). - Removed vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml. Examples, shell scripts, READMEs, and buildkite-invoked tests are updated to use `vllm serve <model> --omni` / `--deploy-config` (auto-load kicks in; no --stage-configs-path or --trust-remote-code). Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
118 lines
3.4 KiB
Python
118 lines
3.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""
|
|
E2E Online tests for MOSS-TTS-Nano model with text input and audio output.
|
|
|
|
These tests verify the /v1/audio/speech endpoint works correctly with
|
|
actual model inference, not mocks.
|
|
"""
|
|
|
|
import os
|
|
|
|
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
|
|
os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "0"
|
|
|
|
import pytest
|
|
|
|
from tests.conftest import OmniServerParams
|
|
from tests.helpers.stage_config import get_deploy_config_path
|
|
from tests.utils import hardware_test
|
|
|
|
MODEL = "OpenMOSS-Team/MOSS-TTS-Nano"
|
|
|
|
|
|
def get_prompt(prompt_type="text"):
|
|
"""Text prompt for text-to-audio tests."""
|
|
prompts = {
|
|
"text": "Hello, this is a test of MOSS-TTS-Nano text to speech synthesis.",
|
|
"chinese": "你好,这是MOSS-TTS-Nano的语音合成测试。",
|
|
}
|
|
return prompts.get(prompt_type, prompts["text"])
|
|
|
|
|
|
tts_server_params = [
|
|
pytest.param(
|
|
OmniServerParams(
|
|
model=MODEL,
|
|
stage_config_path=get_deploy_config_path("moss_tts_nano.yaml"),
|
|
server_args=["--disable-log-stats"],
|
|
),
|
|
id="moss_tts_nano",
|
|
)
|
|
]
|
|
|
|
|
|
@pytest.mark.core_model
|
|
@pytest.mark.advanced_model
|
|
@pytest.mark.omni
|
|
@hardware_test(res={"cuda": "L4"}, num_cards=1)
|
|
@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
|
|
def test_text_to_audio_001(omni_server, openai_client) -> None:
|
|
"""
|
|
Test text input processing and audio output via /v1/audio/speech.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio (48 kHz)
|
|
Input Setting: stream=False, voice=Junhao
|
|
Datasets: single request
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": False,
|
|
"response_format": "wav",
|
|
"voice": "Junhao",
|
|
}
|
|
|
|
openai_client.send_audio_speech_request(request_config)
|
|
|
|
|
|
@pytest.mark.core_model
|
|
@pytest.mark.advanced_model
|
|
@pytest.mark.omni
|
|
@hardware_test(res={"cuda": "L4"}, num_cards=1)
|
|
@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
|
|
def test_text_to_audio_002(omni_server, openai_client) -> None:
|
|
"""
|
|
Test streaming text-to-audio via /v1/audio/speech.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio (48 kHz, PCM stream)
|
|
Input Setting: stream=True, voice=Ava
|
|
Datasets: single request
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": True,
|
|
"response_format": "pcm",
|
|
"voice": "Ava",
|
|
}
|
|
|
|
openai_client.send_audio_speech_request(request_config)
|
|
|
|
|
|
@pytest.mark.core_model
|
|
@pytest.mark.advanced_model
|
|
@pytest.mark.omni
|
|
@hardware_test(res={"cuda": "L4"}, num_cards=1)
|
|
@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
|
|
def test_text_to_audio_003(omni_server, openai_client) -> None:
|
|
"""
|
|
Test Chinese text-to-audio via /v1/audio/speech.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text (Chinese)
|
|
Output Modal: audio (48 kHz)
|
|
Input Setting: stream=False, voice=Junhao
|
|
Datasets: single request
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt("chinese"),
|
|
"stream": False,
|
|
"response_format": "wav",
|
|
"voice": "Junhao",
|
|
}
|
|
|
|
openai_client.send_audio_speech_request(request_config)
|