Skip to content

Torch 2.7 and CUDA 12.8 compile failing #1970

Open
@FurkanGozukara

Description

@FurkanGozukara

I need to compile for RTX 5000 series

I am able to compile Flash Attention, Sage Attention, xFormers and many more in this setup but pytorch3d fails like below

full logs as txt :

full logs.txt

C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/__tuple_dir/vector_types.h(88): error: expected a ">"
  template <> struct tuple_size<unsigned short1> : ::cuda::std::__4::integral_constant<size_t, 1> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short1> { static_assert(_Ip < 1,"tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short2> : ::cuda::std::__4::integral_constant<size_t, 2> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short2> { static_assert(_Ip < 2, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short3> : ::cuda::std::__4::integral_constant<size_t, 3> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short3> { static_assert(_Ip < 3, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short4> : ::cuda::std::__4::integral_constant<size_t, 4> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short4> { static_assert(_Ip < 4, "tuple_element index out of range"); using type = unsigned short; };
                                         ^
16 errors detected in the compilation of "C:/f/pytorch3d/pytorch3d/csrc/pulsar/gpu/renderer.backward.gpu.cu".
renderer.backward.gpu.cu
FAILED: C:/f/pytorch3d/build/temp.win-amd64-cpython-310/Release/f/pytorch3d/pytorch3d/csrc/pulsar/gpu/renderer.calc_signature.gpu.obj

FAILED: C:/f/pytorch3d/build/temp.win-amd64-cpython-310/Release/f/pytorch3d/pytorch3d/csrc/pulsar/gpu/renderer.construct.gpu.obj

FAILED: C:/f/pytorch3d/build/temp.win-amd64-cpython-310/Release/f/pytorch3d/pytorch3d/csrc/pulsar/gpu/renderer.calc_signature.gpu.obj

Microsoft Windows [Version 10.0.26100.3775]
(c) Microsoft Corporation. All rights reserved.

C:\f\venv310\Scripts>activate

(venv310) C:\f\venv310\Scripts>cd..

(venv310) C:\f\venv310>cd..

(venv310) C:\f>git clone --recurse-submodules https://github.com/facebookresearch/pytorch3d
Cloning into 'pytorch3d'...
remote: Enumerating objects: 14967, done.
remote: Counting objects: 100% (2529/2529), done.
remote: Compressing objects: 100% (294/294), done.
remote: Total 14967 (delta 2312), reused 2241 (delta 2235), pack-reused 12438 (from 2)
Receiving objects: 100% (14967/14967), 51.43 MiB | 35.34 MiB/s, done.
Resolving deltas: 100% (10407/10407), done.

(venv310) C:\f>cd pytorch3d

(venv310) C:\f\pytorch3d>python setup.py build_ext bdist_wheel
C:\f\pytorch3d\setup.py:84: UserWarning: The environment variable `CUB_HOME` was not found. NVIDIA CUB is required for compilation and can be downloaded from `https://github.com/NVIDIA/cub/releases`. You can unpack it to a location of your choice and set the environment variable `CUB_HOME` to the folder containing the `CMakeListst.txt` file.
  warnings.warn(
running build_ext
building 'pytorch3d._C' extension
creating C:\f\pytorch3d\build
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\ball_query
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\blending
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\compositing
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\face_areas_normals
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\gather_scatter
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\interp_face_attrs
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\iou_box3d
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\knn
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\marching_cubes
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\mesh_normal_consistency
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\packed_to_padded_tensor
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\point_mesh
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\points_to_volumes
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\gpu
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\host
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\pytorch
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\rasterize_coarse
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\rasterize_meshes
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\rasterize_points
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\sample_farthest_points
creating C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\sample_pdf
C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py:2330: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation.
If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'].
  warnings.warn(
Emitting ninja build file C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/67] C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin\nvcc --generate-dependencies-with-compile --dependency-output C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.obj.d -std=c++17 --use-local-env -Xcompiler /MD -Xcompiler /wd4819 -Xcompiler /wd4251 -Xcompiler /wd4244 -Xcompiler /wd4267 -Xcompiler /wd4275 -Xcompiler /wd4018 -Xcompiler /wd4190 -Xcompiler /wd4624 -Xcompiler /wd4067 -Xcompiler /wd4068 -Xcompiler /EHsc -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -DWITH_CUDA -DTHRUST_IGNORE_CUB_VERSION_CHECK -IC:\f\pytorch3d\pytorch3d\csrc -IC:\f\venv310\lib\site-packages\torch\include -IC:\f\venv310\lib\site-packages\torch\include\torch\csrc\api\include "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -IC:\f\venv310\include -IC:\Python310\include -IC:\Python310\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.26100.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" -c C:\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.cu -o C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.obj -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_120,code=sm_120 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86
FAILED: C:/f/pytorch3d/build/temp.win-amd64-cpython-310/Release/f/pytorch3d/pytorch3d/csrc/pulsar/gpu/renderer.backward.gpu.obj
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin\nvcc --generate-dependencies-with-compile --dependency-output C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.obj.d -std=c++17 --use-local-env -Xcompiler /MD -Xcompiler /wd4819 -Xcompiler /wd4251 -Xcompiler /wd4244 -Xcompiler /wd4267 -Xcompiler /wd4275 -Xcompiler /wd4018 -Xcompiler /wd4190 -Xcompiler /wd4624 -Xcompiler /wd4067 -Xcompiler /wd4068 -Xcompiler /EHsc -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -DWITH_CUDA -DTHRUST_IGNORE_CUB_VERSION_CHECK -IC:\f\pytorch3d\pytorch3d\csrc -IC:\f\venv310\lib\site-packages\torch\include -IC:\f\venv310\lib\site-packages\torch\include\torch\csrc\api\include "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -IC:\f\venv310\include -IC:\Python310\include -IC:\Python310\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.26100.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" -c C:\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.cu -o C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\pulsar\gpu\renderer.backward.gpu.obj -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_120,code=sm_120 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/__tuple_dir/vector_types.h(88): error: expected a ">"
  template <> struct tuple_size<unsigned short1> : ::cuda::std::__4::integral_constant<size_t, 1> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short1> { static_assert(_Ip < 1, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short2> : ::cuda::std::__4::integral_constant<size_t, 2> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short2> { static_assert(_Ip < 2, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short3> : ::cuda::std::__4::integral_constant<size_t, 3> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short3> { static_assert(_Ip < 3, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short4> : ::cuda::std::__4::integral_constant<size_t, 4> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short4> { static_assert(_Ip < 4, "tuple_element index out of range"); using type = unsigned short; };
                                         ^

C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/__tuple_dir/vector_types.h(88): error: expected a ">"
  template <> struct tuple_size<unsigned short1> : ::cuda::std::__4::integral_constant<size_t, 1> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short1> { static_assert(_Ip < 1, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short2> : ::cuda::std::__4::integral_constant<size_t, 2> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short2> { static_assert(_Ip < 2, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short3> : ::cuda::std::__4::integral_constant<size_t, 3> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short3> { static_assert(_Ip < 3, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short4> : ::cuda::std::__4::integral_constant<size_t, 4> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short4> { static_assert(_Ip < 4, "tuple_element index out of range"); using type = unsigned short; };
                                                                                                                                                               ^

C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/__tuple_dir/vector_types.h(88): error: expected a ">"
  template <> struct tuple_size<unsigned short1> : ::cuda::std::__4::integral_constant<size_t, 1> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short1> { static_assert(_Ip < 1, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short2> : ::cuda::std::__4::integral_constant<size_t, 2> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short2> { static_assert(_Ip < 2, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short3> : ::cuda::std::__4::integral_constant<size_t, 3> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short3> { static_assert(_Ip < 3, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short4> : ::cuda::std::__4::integral_constant<size_t, 4> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short4> { static_assert(_Ip < 4, "tuple_element index out of range"); using type = unsigned short; };
                                                                                                                                                                                                                                                                                                            ^

C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/__tuple_dir/vector_types.h(88): error: expected a ">"
  template <> struct tuple_size<unsigned short1> : ::cuda::std::__4::integral_constant<size_t, 1> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short1> { static_assert(_Ip < 1, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short2> : ::cuda::std::__4::integral_constant<size_t, 2> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short2> { static_assert(_Ip < 2, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short3> : ::cuda::std::__4::integral_constant<size_t, 3> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short3> { static_assert(_Ip < 3, "tuple_element index out of range"); using type = unsigned short; }; template <> struct tuple_size<unsigned short4> : ::cuda::std::__4::integral_constant<size_t, 4> {}; template <size_t _Ip> struct tuple_element<_Ip, unsigned short4> { static_assert(_Ip < 4, "tuple_element index out of range"); using type = unsigned short; };
       

  .
.
.
.
.
.
.
.
.                                                                                                                                                                                                                                                                                                                                                                                                                      

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

point_mesh_cuda.cu
tmpxft_0000d230_00000000-7_point_mesh_cuda.compute_86.cudafe1.cpp
[32/67] C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin\nvcc --generate-dependencies-with-compile --dependency-output C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\points_to_volumes\points_to_volumes.obj.d -std=c++17 --use-local-env -Xcompiler /MD -Xcompiler /wd4819 -Xcompiler /wd4251 -Xcompiler /wd4244 -Xcompiler /wd4267 -Xcompiler /wd4275 -Xcompiler /wd4018 -Xcompiler /wd4190 -Xcompiler /wd4624 -Xcompiler /wd4067 -Xcompiler /wd4068 -Xcompiler /EHsc -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -DWITH_CUDA -DTHRUST_IGNORE_CUB_VERSION_CHECK -IC:\f\pytorch3d\pytorch3d\csrc -IC:\f\venv310\lib\site-packages\torch\include -IC:\f\venv310\lib\site-packages\torch\include\torch\csrc\api\include "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -IC:\f\venv310\include -IC:\Python310\include -IC:\Python310\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.26100.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" -c C:\f\pytorch3d\pytorch3d\csrc\points_to_volumes\points_to_volumes.cu -o C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\points_to_volumes\points_to_volumes.obj -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_120,code=sm_120 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/detail/libcxx/include/cmath(1032): warning #221-D: floating-point value does not fit in required floating-point type
    if (__r >= ::nextafter(static_cast<_RealT>(_MaxVal), ((float)(1e+300))))
                                                          ^

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

points_to_volumes.cu
tmpxft_0000d4bc_00000000-7_points_to_volumes.compute_86.cudafe1.cpp
[33/67] C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin\nvcc --generate-dependencies-with-compile --dependency-output C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\iou_box3d\iou_box3d.obj.d -std=c++17 --use-local-env -Xcompiler /MD -Xcompiler /wd4819 -Xcompiler /wd4251 -Xcompiler /wd4244 -Xcompiler /wd4267 -Xcompiler /wd4275 -Xcompiler /wd4018 -Xcompiler /wd4190 -Xcompiler /wd4624 -Xcompiler /wd4067 -Xcompiler /wd4068 -Xcompiler /EHsc -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -DWITH_CUDA -DTHRUST_IGNORE_CUB_VERSION_CHECK -IC:\f\pytorch3d\pytorch3d\csrc -IC:\f\venv310\lib\site-packages\torch\include -IC:\f\venv310\lib\site-packages\torch\include\torch\csrc\api\include "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -IC:\f\venv310\include -IC:\Python310\include -IC:\Python310\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.26100.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" -c C:\f\pytorch3d\pytorch3d\csrc\iou_box3d\iou_box3d.cu -o C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\iou_box3d\iou_box3d.obj -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_120,code=sm_120 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/detail/libcxx/include/cmath(1032): warning #221-D: floating-point value does not fit in required floating-point type
    if (__r >= ::nextafter(static_cast<_RealT>(_MaxVal), ((float)(1e+300))))
                                                          ^

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

iou_box3d.cu
tmpxft_0000ac74_00000000-7_iou_box3d.compute_86.cudafe1.cpp
[34/67] C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin\nvcc --generate-dependencies-with-compile --dependency-output C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\knn\knn.obj.d -std=c++17 --use-local-env -Xcompiler /MD -Xcompiler /wd4819 -Xcompiler /wd4251 -Xcompiler /wd4244 -Xcompiler /wd4267 -Xcompiler /wd4275 -Xcompiler /wd4018 -Xcompiler /wd4190 -Xcompiler /wd4624 -Xcompiler /wd4067 -Xcompiler /wd4068 -Xcompiler /EHsc -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -DWITH_CUDA -DTHRUST_IGNORE_CUB_VERSION_CHECK -IC:\f\pytorch3d\pytorch3d\csrc -IC:\f\venv310\lib\site-packages\torch\include -IC:\f\venv310\lib\site-packages\torch\include\torch\csrc\api\include "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\include" -IC:\f\venv310\include -IC:\Python310\include -IC:\Python310\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.42.34433\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.26100.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.26100.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" -c C:\f\pytorch3d\pytorch3d\csrc\knn\knn.cu -o C:\f\pytorch3d\build\temp.win-amd64-cpython-310\Release\f\pytorch3d\pytorch3d\csrc\knn\knn.obj -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_120,code=sm_120 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86
C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8/include\cuda/std/detail/libcxx/include/cmath(1032): warning #221-D: floating-point value does not fit in required floating-point type
    if (__r >= ::nextafter(static_cast<_RealT>(_MaxVal), ((float)(1e+300))))
                                                          ^

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

knn.cu
tmpxft_0000cd18_00000000-7_knn.compute_86.cudafe1.cpp
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py", line 2480, in _run_ninja_build
    subprocess.run(
  File "C:\Python310\lib\subprocess.py", line 526, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\f\pytorch3d\setup.py", line 144, in <module>
    setup(
  File "C:\f\venv310\lib\site-packages\setuptools\__init__.py", line 87, in setup
    return distutils.core.setup(**attrs)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\core.py", line 185, in setup
    return run_commands(dist)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\core.py", line 201, in run_commands
    dist.run_commands()
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\dist.py", line 968, in run_commands
    self.run_command(cmd)
  File "C:\f\venv310\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\dist.py", line 987, in run_command
    cmd_obj.run()
  File "C:\f\venv310\lib\site-packages\setuptools\command\build_ext.py", line 84, in run
    _build_ext.run(self)
  File "C:\f\venv310\lib\site-packages\Cython\Distutils\old_build_ext.py", line 186, in run
    _build_ext.build_ext.run(self)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 346, in run
    self.build_extensions()
  File "C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py", line 1007, in build_extensions
    build_ext.build_extensions(self)
  File "C:\f\venv310\lib\site-packages\Cython\Distutils\old_build_ext.py", line 195, in build_extensions
    _build_ext.build_ext.build_extensions(self)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 466, in build_extensions
    self._build_extensions_serial()
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 492, in _build_extensions_serial
    self.build_extension(ext)
  File "C:\f\venv310\lib\site-packages\setuptools\command\build_ext.py", line 246, in build_extension
    _build_ext.build_extension(self, ext)
  File "C:\f\venv310\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 547, in build_extension
    objects = self.compiler.compile(
  File "C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py", line 975, in win_wrap_ninja_compile
    _write_ninja_file_and_compile_objects(
  File "C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py", line 2133, in _write_ninja_file_and_compile_objects
    _run_ninja_build(
  File "C:\f\venv310\lib\site-packages\torch\utils\cpp_extension.py", line 2496, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension

(venv310) C:\f\pytorch3d>

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions