How Pytorch process pybind11 c++11 module when export to ONNX model

In my code, some ops are implemented as pybin11,i.e., python called c++ module,
like this

#!/usr/bin/env python

import os
import glob

import torch

from torch.utils.cpp_extension import CUDA_HOME
from torch.utils.cpp_extension import CppExtension
from torch.utils.cpp_extension import CUDAExtension

from setuptools import find_packages
from setuptools import setup

requirements = ["torch", "torchvision"]


def get_extensions():
    this_dir = os.path.dirname(os.path.abspath(__file__))
    extensions_dir = os.path.join(this_dir, "smoke", "csrc")

    main_file = glob.glob(os.path.join(extensions_dir, "*.cpp"))
    source_cpu = glob.glob(os.path.join(extensions_dir, "cpu", "*.cpp"))
    source_cuda = glob.glob(os.path.join(extensions_dir, "cuda", "*.cu"))

    sources = main_file + source_cpu
    extension = CppExtension

    extra_compile_args = {"cxx": []}
    define_macros = []

    if torch.cuda.is_available() and CUDA_HOME is not None:
        extension = CUDAExtension
        sources += source_cuda
        define_macros += [("WITH_CUDA", None)]
        extra_compile_args["nvcc"] = [
            "-DCUDA_HAS_FP16=1",  # Whether a short float (float16,fp16) is supported.
            "-D__CUDA_NO_HALF_OPERATORS__", # https://github.com/pytorch/pytorch/blob/master/cmake/Dependencies.cmake#L1117
            "-D__CUDA_NO_HALF_CONVERSIONS__",
            "-D__CUDA_NO_HALF2_OPERATORS__",
        ]
    else:
        raise NotImplementedError("cuda is not available")

    sources = [os.path.join(extensions_dir, s) for s in sources]

    include_dirs = [extensions_dir]

    ext_modules = [
        extension(
            "smoke._ext",
            sources,
            include_dirs=include_dirs,
            define_macros=define_macros,
            extra_compile_args=extra_compile_args,
        )
    ]

    return ext_modules

setup(
    name="smoke",
    version="0.1",
    author="lzccccc",
    url="https://github.com/lzccccc/SMOKE",
    description="Single-Stage Monocular 3D Object Detection via Keypoint Estimation",
    packages=find_packages(exclude=("configs", "tests",)),
    ext_modules=get_extensions(),
    cmdclass={"build_ext": torch.utils.cpp_extension.BuildExtension},
)

and it produced
_ext.cpython-39-x86_64-linux-gnu.so

and _ext.cpython-39-x86_64-linux-gnu.so is used by module :

#other code is omitted 

from smoke import _ext as _backend

class _DCNv2(Function):
    @staticmethod
    def forward(ctx, input, offset, mask, weight, bias,
                stride, padding, dilation, deformable_groups):
        ctx.stride = _pair(stride)
        ctx.padding = _pair(padding)
        ctx.dilation = _pair(dilation)
        ctx.kernel_size = _pair(weight.shape[2:4])
        ctx.deformable_groups = deformable_groups
        output = _backend.dcn_v2_forward(input, weight, bias,
                                         offset, mask,
                                         ctx.kernel_size[0], ctx.kernel_size[1],
                                         ctx.stride[0], ctx.stride[1],
                                         ctx.padding[0], ctx.padding[1],
                                         ctx.dilation[0], ctx.dilation[1],
                                         ctx.deformable_groups)
        ctx.save_for_backward(input, offset, mask, weight, bias)
        return output

    @staticmethod
    @once_differentiable
    def backward(ctx, grad_output):
        input, offset, mask, weight, bias = ctx.saved_tensors
        grad_input, grad_offset, grad_mask, grad_weight, grad_bias = \
            _backend.dcn_v2_backward(input, weight,
                                     bias,
                                     offset, mask,
                                     grad_output,
                                     ctx.kernel_size[0], ctx.kernel_size[1],
                                     ctx.stride[0], ctx.stride[1],
                                     ctx.padding[0], ctx.padding[1],
                                     ctx.dilation[0], ctx.dilation[1],
                                     ctx.deformable_groups)

        return grad_input, grad_offset, grad_mask, grad_weight, grad_bias, \
               None, None, None, None,


dcn_v2_conv = _DCNv2.apply

when we exports model of .pth to ONNX format(.onnx), does ONNX converter recognize this module produced by C++11?