c9370f493e
Signed-off-by: yenuo26 <410167048@qq.com> Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com> Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Signed-off-by: wangyu <410167048@qq.com> Co-authored-by: yenuo26 <410167048@example.com> Co-authored-by: R2-Y <ruiruyang2@gmail.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
106 lines
3.2 KiB
Python
106 lines
3.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""
|
|
E2E Online tests for Qwen3-TTS 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"
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tests.conftest import OmniServerParams
|
|
from tests.utils import hardware_test
|
|
|
|
MODEL = "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"
|
|
|
|
|
|
def get_stage_config(name: str = "qwen3_tts.yaml"):
|
|
"""Get the stage config path from vllm_omni model_executor stage_configs."""
|
|
return str(Path(__file__).parent.parent.parent.parent / "vllm_omni" / "model_executor" / "stage_configs" / name)
|
|
|
|
|
|
def get_prompt(prompt_type="text"):
|
|
"""Text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case)."""
|
|
prompts = {
|
|
"text": "Beijing, China's capital, blends ancient wonders like the Great Wall with modern marvels. This vibrant metropolis offers rich culture, delicious Peking duck, and endless exploration opportunities.",
|
|
}
|
|
return prompts.get(prompt_type, prompts["text"])
|
|
|
|
|
|
def get_max_batch_size(size_type="few"):
|
|
"""Batch size for concurrent requests (same as test_qwen3_omni)."""
|
|
batch_sizes = {"few": 5, "medium": 100, "large": 256}
|
|
return batch_sizes.get(size_type, 5)
|
|
|
|
|
|
tts_server_params = [
|
|
pytest.param(
|
|
OmniServerParams(
|
|
model=MODEL,
|
|
stage_config_path=get_stage_config("qwen3_tts.yaml"),
|
|
server_args=["--trust-remote-code", "--disable-log-stats"],
|
|
),
|
|
id="async_chunk",
|
|
)
|
|
]
|
|
|
|
|
|
@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 OpenAI API.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio
|
|
Input Setting: stream=False
|
|
Datasets: few requests
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": False,
|
|
"response_format": "wav",
|
|
"task_type": "CustomVoice",
|
|
"voice": "vivian",
|
|
}
|
|
|
|
openai_client.send_audio_speech_request(request_config, request_num=get_max_batch_size())
|
|
|
|
|
|
@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 text input processing and audio output via OpenAI API.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio
|
|
Input Setting: stream=True
|
|
Datasets: single request
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": True,
|
|
"response_format": "wav",
|
|
"task_type": "CustomVoice",
|
|
"voice": "vivian",
|
|
}
|
|
|
|
openai_client.send_audio_speech_request(request_config)
|