multiple definition of "

Hi I am trying to build a custom python package which includes cuda files and corresponding cpp and header files. My directory structure looks like this

Apology for a bit long question below. I am not quite sure the exact location of error hence I am putting up most of the relevant stuff.

The header files are as follows -

utils.h

#pragma once
#include <ATen/cuda/CUDAContext.h>
#include <torch/extension.h>

#define CHECK_CUDA(x)                                    \
  do                                                     \
  {                                                      \
    AT_ASSERT(x.is_cuda(), #x " must be a CUDA tensor"); \
  } while (0)

cuda_utils.h

#ifndef _CUDA_UTILS_H
#define _CUDA_UTILS_H

#include <ATen/ATen.h>
#include <ATen/cuda/CUDAContext.h>
#include <cmath>

#include <cuda.h>
#include <cuda_runtime.h>

#include <vector>

#define TOTAL_THREADS 512

inline int opt_n_threads(int work_size)
{
  const int pow_2 = std::log(static_cast<double>(work_size)) / std::log(2.0);

  return max(min(1 << pow_2, TOTAL_THREADS), 1);
}

#define CUDA_CHECK_ERRORS()                                           \
  do                                                                  \
  {                                                                   \
    cudaError_t err = cudaGetLastError();                             \
    if (cudaSuccess != err)                                           \
    {                                                                 \
      fprintf(stderr, "CUDA kernel failed : %s\n%s at L:%d in %s\n",  \
              cudaGetErrorString(err), __PRETTY_FUNCTION__, __LINE__, \
              __FILE__);                                              \
      exit(-1);                                                       \
    }                                                                 \
  } while (0)

#endif

cuda_test.h

#pragma once
#include <torch/extension.h>

at::Tensor cuda_test(
    at::Tensor verts_list,
    at::Tensor verts_list_length,
    const float radius,
    const int nsample,
    const int current_nearest_vertex_index);

The CUDA file

cuda_test.cu

#include <math.h>
#include <stdio.h>
#include <stdlib.h>

#include "cuda_utils.h"

__global__ void query(int b, float radius,
    int nsample, int current_nearest_vertex_index,
    const float *__restrict__ verts_list,
    const int *__restrict__ verts_list_length
    int *__restrict__ query_idx)
{
      int batch_idx = blockIdx.x;
      <some implementation>
}

void query_wrapper(int b, float radius,
        int nsample, int current_nearest_vertex_index,
        const float *verts_list,
        const int *verts_list_length,
        int *query_idx
        )
{   
    cudaStream_t stream = at::cuda::getCurrentCUDAStream();
    query<<<b, opt_n_threads(1), 0, stream>>>(b, radius,
        nsample, current_nearest_vertex_index,
        verts_list,
        verts_list_length,
        query_idx);
    
    CUDA_CHECK_ERRORS();
}

The CPP file to link with the cuda file cuda_test.cpp

#include "cuda_test.h"
#include "utils.h"

void query_wrapper(int b, float radius,
                   int nsample,
                   int current_nearest_vertex_index,
                   const float *verts_list,
                   const int *verts_list_length,
                   int *query_idx);

at::Tensor cuda_test(
    at::Tensor verts_list,
    at::Tensor verts_list_length,
    const float radius,
    const int nsample,
    const int current_nearest_vertex_index)
{
        CHECK_CONTIGUOUS(verts_list);
        CHECK_IS_FLOAT(verts_list);
        CHECK_CONTIGUOUS(verts_list_length);
        CHECK_IS_INT(verts_list_length);

        at::Tensor query_idx =
            torch::zeros({verts_list.size(0), nsample},
                         at::device(verts_list.device()).dtype(at::ScalarType::Int));
        if (verts_list.is_cuda())
        {
                query_wrapper(verts_list.size(0), radius,
                              nsample,
                              current_nearest_vertex_index,
                              verts_list.data_ptr<float>(),
                              verts_list_length.data_ptr<int>(),
                              query_idx.data_ptr<int>());
        }
        else
        {
                AT_ASSERT(false, "CPU not supported");
        }
        return idx;
}

The bindings.cpp

#include "cuda_test.h"

PYBIND11_MODULE(TORCH_EXTENSION_NAME, m)
{
  m.def("cuda_test", &cuda_test);
}

I tried to build and install this but I am getting the following error

build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o: In function `__device_stub__Z5queryifiiPKfPKiPi(int, float, int, int, float const*, int const*, int*)':
tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x10): multiple definition of `__device_stub__Z5queryifiiPKfPKiPi(int, float, int, int, float const*, int const*, int*)'
build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o:tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x10): first defined here
build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o: In function `query(int, float, int, int, float const*, int const*, int*)':
tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x180): multiple definition of `query(int, float, int, int, float const*, int const*, int*)'
build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o:tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x180): first defined here
build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o: In function `query_wrapper(int, float, int, int, float const*, int const*, int*)':
tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x190): multiple definition of `query_wrapper(int, float, int, int, float const*, int const*, int*)'
build/temp.linux-x86_64-3.7/test_ops/_ext-src/src/cuda_test.o:tmpxft_000001a4_00000000-6_cuda_test.compute_75.cudafe1.cpp:(.text+0x190): first defined here
collect2: error: ld returned 1 exit status

I followed the exact structure from this link which is building totally correct. I think I have done everything right whatever I could.

Am I making any error in my build and install? Thank you in advance!!