[Entrypoint][Refactor] vLLM-Omni Entrypoint Refactoring (#1908)

Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
Signed-off-by: Peiqi Yin <yinpeiqi809@gmail.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: wuhang <whlbx@hotmail.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
Signed-off-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: yinpe <11810305@mail.sustech.edu.cn>
Co-authored-by: Peiqi Yin <yinpeiqi809@gmail.com>
Co-authored-by: wuhang <whlbx@hotmail.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: lishunyang <lishunyang12@163.com>
This commit is contained in:
authored and GitHub committed 2026-03-18 17:33:53 +08:00
1 parent 6a66a1fe36
commit 3158e9d28f
125 files changed
+5210 -9322

No files matched your search

+59 -13
View File
@@ -11,6 +11,7 @@ import time
import traceback
from collections.abc import Iterable, Sequence
from enum import StrEnum, auto
from types import SimpleNamespace
from typing import Any, NamedTuple
from unittest.mock import AsyncMock, MagicMock, patch
@@ -31,6 +32,7 @@ from vllm import SamplingParams
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm_omni.entrypoints.async_omni import AsyncOmni as RealAsyncOmni
from vllm_omni.entrypoints.cli.serve import OmniServeCommand
from vllm_omni.inputs.data import OmniSamplingParams
from vllm_omni.outputs import OmniRequestOutput
@@ -43,7 +45,7 @@ class ServerCase(NamedTuple):
served_model: str
stage_list: list
stage_configs: list[dict]
stage_configs: list[Any]
outputs: list[OmniRequestOutput]
@@ -262,6 +264,40 @@ def _assert_model_param_values(received: OmniSamplingParams, expected: dict):
)
def _make_stage_config(
stage_type: str,
*,
is_comprehension: bool = False,
model_stage: str | None = None,
):
engine_args = SimpleNamespace()
if model_stage is not None:
engine_args.model_stage = model_stage
return SimpleNamespace(
stage_type=stage_type,
is_comprehension=is_comprehension,
engine_args=engine_args,
)
def _stage_type(stage: Any) -> str | None:
return getattr(stage, "stage_type", None)
def _build_output_modalities(stage_configs: list[Any]) -> list[str]:
modalities: list[str] = []
for stage in stage_configs:
final_output = getattr(stage, "final_output", False)
final_output_type = getattr(stage, "final_output_type", None)
if final_output and isinstance(final_output_type, str):
modalities.append(final_output_type)
if modalities:
return modalities
if any(_stage_type(stage) == "diffusion" for stage in stage_configs):
return ["image"]
return ["text", "audio"]
def _build_mock_outputs(outputs: Iterable[OmniRequestOutput], sampling_case: SamplingCase, server_case: ServerCase):
async def _mock_generate(*args, **kwargs):
received_sampling_params_list: Sequence[OmniSamplingParams] | None = (
@@ -367,18 +403,28 @@ def mock_async_omni(server_case: ServerCase, sampling_case: SamplingCase):
new=_mock_preprocess_chat,
),
):
mock_instance = AsyncMock()
mock_instance = AsyncMock(spec=RealAsyncOmni)
mock_instance.generate = _build_mock_outputs(server_case.outputs, sampling_case, server_case)
mock_instance.stage_list = server_case.stage_list
mock_instance.stage_configs = server_case.stage_configs
mock_instance.output_modalities = _build_output_modalities(server_case.stage_configs)
mock_instance.default_sampling_params_list = [
SamplingParams() if stage.get("stage_type") != "diffusion" else MagicMock()
SamplingParams() if _stage_type(stage) != "diffusion" else MagicMock()
for stage in server_case.stage_configs
]
mock_instance.errored = False
mock_instance.dead_error = RuntimeError("Mock engine error")
mock_instance.model_config = MagicMock(max_model_len=4096, io_processor_plugin=None)
mock_instance.model_config = MagicMock(
max_model_len=4096,
io_processor_plugin=None,
allowed_local_media_path=None,
allowed_media_domains=None,
)
# Mimic Qwen3-TTS talker speaker config so CustomVoice validation passes.
mock_instance.model_config.hf_config = MagicMock()
mock_instance.model_config.hf_config.talker_config = MagicMock()
mock_instance.model_config.hf_config.talker_config.speaker_id = {"Vivian": 0}
mock_instance.io_processor = MagicMock()
mock_instance.input_processor = MagicMock()
mock_instance.shutdown = MagicMock()
@@ -444,7 +490,7 @@ def api_server(unused_tcp_port_factory, server_case: ServerCase, mock_async_omni
ServerCase(
served_model="Tongyi-MAI/Z-Image-Turbo",
stage_list=["diffusion"],
stage_configs=[{"stage_type": "diffusion"}],
stage_configs=[_make_stage_config("diffusion")],
outputs=[_build_diffusion_image_output_for_images_endpoint()],
),
"Tongyi-MAI/Z-Image-Turbo",
@@ -455,7 +501,7 @@ def api_server(unused_tcp_port_factory, server_case: ServerCase, mock_async_omni
ServerCase(
served_model="ByteDance-Seed/BAGEL-7B-MoT",
stage_list=["diffusion"],
stage_configs=[{"stage_type": "diffusion"}],
stage_configs=[_make_stage_config("diffusion")],
outputs=[_build_diffusion_image_output_for_chat_endpoint()],
),
"ByteDance-Seed/BAGEL-7B-MoT",
@@ -466,7 +512,7 @@ def api_server(unused_tcp_port_factory, server_case: ServerCase, mock_async_omni
ServerCase(
served_model="Qwen/Qwen-Image-Edit",
stage_list=["diffusion"],
stage_configs=[{"stage_type": "diffusion"}],
stage_configs=[_make_stage_config("diffusion")],
outputs=[_build_diffusion_image_output_for_images_endpoint()],
),
"Qwen/Qwen-Image-Edit",
@@ -477,7 +523,7 @@ def api_server(unused_tcp_port_factory, server_case: ServerCase, mock_async_omni
ServerCase(
served_model="ByteDance-Seed/BAGEL-7B-MoT",
stage_list=["diffusion"],
stage_configs=[{"stage_type": "diffusion"}],
stage_configs=[_make_stage_config("diffusion")],
outputs=[_build_diffusion_image_output_for_chat_endpoint()],
),
"ByteDance-Seed/BAGEL-7B-MoT",
@@ -542,9 +588,9 @@ async def test_image_generation_node(api_server: str, model: str, image_input: b
MagicMock(is_comprehension=False, model_stage="llm"),
],
stage_configs=[
{"stage_type": "llm"},
{"stage_type": "llm"},
{"stage_type": "llm"},
_make_stage_config("llm", is_comprehension=True, model_stage="thinker"),
_make_stage_config("llm", is_comprehension=False, model_stage="talker"),
_make_stage_config("llm", is_comprehension=False, model_stage="code2wav"),
],
outputs=[_build_audio_chat_output(), _build_text_output("Understanding response")],
),
@@ -599,7 +645,7 @@ async def test_understanding_node(api_server: str, sampling_case: SamplingCase):
ServerCase(
served_model="Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
stage_list=["llm"],
stage_configs=[{"stage_type": "llm"}],
stage_configs=[_make_stage_config("llm", model_stage="qwen3_tts")],
outputs=[_build_audio_speech_output()],
),
VLLMOmniTTS,
@@ -617,7 +663,7 @@ async def test_understanding_node(api_server: str, sampling_case: SamplingCase):
ServerCase(
served_model="Qwen/Qwen3-TTS-12Hz-1.7B-Base",
stage_list=["llm"],
stage_configs=[{"stage_type": "llm"}],
stage_configs=[_make_stage_config("llm", model_stage="qwen3_tts")],
outputs=[_build_audio_speech_output()],
),
VLLMOmniVoiceClone,