[Bug] Multi-process engine not working

### Checklist

- [x] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
- [x] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

### Describe the bug

When I try to serve using pytorch backend with python code I run into the error below. Even if enable_mp_engine is False, it'll automatically set to True because of the code in serve/openai/api_server.py:1350. So mp engine is not working, nor can be turned off.

### Reproduction

```python
from lmdeploy import PytorchEngineConfig, serve

model_path = "Qwen/Qwen3-0.6B"

engine_config = PytorchEngineConfig(
session_len=500,
dtype="float16",
)
if __name__ == '__main__':
serve(
model_path = model_path,
backend = 'pytorch',
backend_config = engine_config,
server_port = 8080,
log_level = 'DEBUG',
)
while(True):
pass
```

### Environment

```Shell
sys.platform: linux
Python: 3.12.3 (main, Jun 18 2025, 17:59:45) [GCC 13.3.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce GTX 1650 with Max-Q Design
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 12.0, V12.0.140
GCC: x86_64-linux-gnu-gcc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
PyTorch: 2.6.0+cu124
PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201703
- Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 12.4
- NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
- CuDNN 90.1
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=2236df1770800ffea5697b11b0bb0d910b2e59e1, CUDA_VERSION=12.4, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.6.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

TorchVision: 0.21.0+cu124
LMDeploy: 0.9.2+
transformers: 4.51.3
gradio: Not Found
fastapi: 0.115.12
pydantic: 2.11.3
triton: 3.2.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-7 0 N/A

Legend:

X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLink
```

### Error traceback

```Shell
2025-07-27 14:11:42,996 - lmdeploy - INFO - async_engine.py:266 - input backend=pytorch, backend_config=PytorchEngineConfig(dtype='float16', tp=1, dp=1, dp_rank=0, ep=1, session_len=500, max_batch_size=None, cache_max_entry_count=0.8, prefill_interval=16, block_size=64, num_cpu_blocks=0, num_gpu_blocks=0, adapters=None, max_prefill_token_num=4096, thread_safe=False, enable_prefix_caching=False, device_type='cuda', eager_mode=False, custom_module_map=None, download_dir=None, revision=None, quant_policy=0, distributed_executor_backend=None, empty_init=False, enable_microbatch=False, enable_eplb=False, enable_mp_engine=True, model_format=None, enable_metrics=False, hf_overrides=None, disable_vision_encoder=False, role=, migration_backend=)
2025-07-27 14:11:42,997 - lmdeploy - INFO - async_engine.py:267 - input chat_template_config=None
2025-07-27 14:11:43,879 - lmdeploy - INFO - async_engine.py:276 - updated chat_template_onfig=ChatTemplateConfig(model_name='qwen3', system=None, meta_instruction=None, eosys=None, user=None, eoh=None, assistant=None, eoa=None, tool=None, eotool=None, separator=None, capability=None, stop_words=None)
2025-07-27 14:11:48,373 - lmdeploy - DEBUG - __init__.py:7 - Registering DLSlime Backend
2025-07-27 14:11:48,373 - lmdeploy - WARNING - __init__.py:10 - Disable DLSlime Backend
2025-07-27 14:11:48,373 - lmdeploy - DEBUG - __init__.py:13 - Registering Mooncake Backend
2025-07-27 14:11:49,349 - lmdeploy - DEBUG - mp_engine.py:98 - Starting engine multi-process.
Process Process-1:
Traceback (most recent call last):
File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/serve/openai/api_server.py", line 1352, in serve
VariableInterface.async_engine = pipeline_class(model_path=model_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/serve/async_engine.py", line 286, in init
self._build_pytorch(model_path=model_path, backend_config=backend_config, **kwargs)
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/serve/async_engine.py", line 351, in _build_pytorch
self.engine = Engine.from_pretrained(model_path, tokenizer=self.tokenizer, engine_config=backend_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/pytorch/engine/engine.py", line 424, in from_pretrained
return MPEngine(model_path=pretrained_model_name_or_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/pytorch/engine/mp_engine/mp_engine.py", line 89, in init
self._start_mp_proc(model_path, tokenizer, engine_config)
File "/home/user/lmdeployvenv/lib/python3.12/site-packages/lmdeploy/pytorch/engine/mp_engine/mp_engine.py", line 104, in _start_mp_proc
with mp.Manager() as manager:
^^^^^^^^^^^^
File "/usr/lib/python3.12/multiprocessing/context.py", line 57, in Manager
m.start()
File "/usr/lib/python3.12/multiprocessing/managers.py", line 562, in start
self._process.start()
File "/usr/lib/python3.12/multiprocessing/process.py", line 118, in start
assert not _current_process._config.get('daemon'), \
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: daemonic processes are not allowed to have children
```