[Build] Error trying to build ORT with Tensorrt EP on Windows #23378
Comments
github-actions
bot
added
ep:TensorRT
guschmue
removed
the
platform:web
|
Try upgrade cmake to 3.31.4 and Install cudnn 9.x. Example build comand: |
|
Thank you for your answer, @tianleiwu . after cmake update and cudnn download, i run: but other errors occur. Below the output of my compilation: 2025-01-16 09:36:52,061 build [DEBUG] - Command line arguments: [notice] A new release of pip is available: 24.0 -> 24.3.1 The cmake-policies(7) manual explains that the OLD behaviors of all -- Selecting Windows SDK version 10.0.22621.0 to target Windows 10.0.22631. is not able to compile a simple test program. It fails with the following output: CMake will not be able to correctly generate this project. -- Configuring incomplete, errors occurred! |
|
You can follow the error message
|
Describe the issue
I am trying to build onnxruntime with tensorrt EP, but following the documentation an error occurs.
Below the version of the adopted libraries:
TensorRT Version: 10.5.0.18
NVIDIA GPU: Quadro T1000
NVIDIA Driver Version: 553.50
CUDA Version: 12.2
CUDNN Version: 8.9
Operating System: Windows 11 Pro 23H2
Thank you for your help.
Urgency
An important project for my company is blocked because of this problem
Target platform
x64 - Windows
Build script
.\build.bat --cudnn_home "C:\Program Files\NVIDIA\CUDNN\v8.9" --cuda_home "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2" --use_tensorrt --tensorrt_home "E:\Libraries\TensorRT-10.5.0.18" --cmake_generator "Visual Studio 17 2022"Error / output
1>Checking Build System
1>
Building Custom Rule E:/repository/onnxruntime/build/Windows/Debug/_deps/microsoft_wil-subbuild/CMakeLists.txt
Building Custom Rule E:/repository/onnxruntime/build/Windows/Debug/_deps/microsoft_wil-subbuild/CMakeLists.txt
-- cudnn found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn.lib.
-- cuDNN: C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn.lib
-- cuDNN: C:/Program Files/NVIDIA/CUDNN/v8.9/include
-- cudnn_adv_infer found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_adv_infer.lib.
-- cudnn_adv_train found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_adv_train.lib.
-- cudnn_cnn_infer found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_cnn_infer.lib.
-- cudnn_cnn_train found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_cnn_train.lib.
-- cudnn_ops_infer found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_ops_infer.lib.
-- cudnn_ops_train found at C:/Program Files/NVIDIA/CUDNN/v8.9/lib/cudnn_ops_train.lib.
-- Finished fetching external dependencies
CMake Error at C:/Program Files/CMake/share/cmake-3.28/Modules/CMakeDetermineCompilerId.cmake:780 (message):
Compiling the CUDA compiler identification source file
"CMakeCUDACompilerId.cu" failed.
Compiler: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2/bin/nvcc
Build flags: -allow-unsupported-compiler
Id flags: --keep;--keep-dir;tmp -v
The output was:
1
MSBuild version 17.11.9+a69bbaaf5 for .NET Framework
Build started 15/01/2025 10:02:24.
Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
on node 1 (default targets).
PrepareForBuild:
InitializeBuildStatus:
AddCudaCompileDeps:
Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(1) is building
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(1:2) on node 1 (CudaBuildCore target(s)).
CudaBuildCore:
C:\Program Files\NVIDIA GPU Computing
Toolkit\CUDA\v12.2\include\crt/host_config.h(157): fatal error C1189:
#error: -- unsupported Microsoft Visual Studio version! Only the versions
between 2017 and 2022 (inclusive) are supported! The nvcc flag
'-allow-unsupported-compiler' can be used to override this version check;
however, using an unsupported host compiler may cause compilation failure
or incorrect run time execution. Use at your own risk.
[E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj]
C:\Program Files\NVIDIA GPU Computing
Toolkit\CUDA\v12.2\extras\visual_studio_integration\MSBuildExtensions\CUDA
12.2.targets(799,9): error MSB3721: The command ""C:\Program Files\NVIDIA
GPU Computing Toolkit\CUDA\v12.2\bin\nvcc.exe"
-gencode=arch=compute_52,code="sm_52,compute_52" --use-local-env -ccbin
"C:\Program Files\Microsoft Visual
Studio\2022\Community\VC\Tools\MSVC\14.41.34120\bin\HostX64\x64" -x cu
-I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\include"
-I"E:\repository\vcpkg\installed\x64-windows\include" -I"C:\Program
Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\include" -G --keep-dir
CompilerIdCUDA\x64\Debug -maxrregcount=0 --machine 64 --compile -cudart
static -v -g -D_MBCS -Xcompiler "/EHsc /W0 /nologo /Od /FS /Zi /RTC1 /MDd "
-Xcompiler "/FdDebug\vc143.pdb" -o
E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA\x64\Debug\CMakeCUDACompilerId.cu.obj
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CMakeCUDACompilerId.cu""
exited with code 2.
[E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj]
Done Building Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(CudaBuildCore target(s)) -- FAILED.
Done Building Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(default targets) -- FAILED.
Build FAILED.
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(default target) (1) ->
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(CudaBuildCore target) (1:2) ->
(CudaBuildCore target) ->
Time Elapsed 00:00:00.70
Compiling the CUDA compiler identification source file
"CMakeCUDACompilerId.cu" failed.
Compiler: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2/bin/nvcc
Build flags:
Id flags: --keep;--keep-dir;tmp -v
The output was:
1
MSBuild version 17.11.9+a69bbaaf5 for .NET Framework
Build started 15/01/2025 10:02:25.
Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
on node 1 (default targets).
PrepareForBuild:
InitializeBuildStatus:
AddCudaCompileDeps:
Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(1) is building
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(1:2) on node 1 (CudaBuildCore target(s)).
CudaBuildCore:
C:\Program Files\NVIDIA GPU Computing
Toolkit\CUDA\v12.2\include\crt/host_config.h(157): fatal error C1189:
#error: -- unsupported Microsoft Visual Studio version! Only the versions
between 2017 and 2022 (inclusive) are supported! The nvcc flag
'-allow-unsupported-compiler' can be used to override this version check;
however, using an unsupported host compiler may cause compilation failure
or incorrect run time execution. Use at your own risk.
[E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj]
C:\Program Files\NVIDIA GPU Computing
Toolkit\CUDA\v12.2\extras\visual_studio_integration\MSBuildExtensions\CUDA
12.2.targets(799,9): error MSB3721: The command ""C:\Program Files\NVIDIA
GPU Computing Toolkit\CUDA\v12.2\bin\nvcc.exe"
-gencode=arch=compute_52,code="sm_52,compute_52" --use-local-env -ccbin
"C:\Program Files\Microsoft Visual
Studio\2022\Community\VC\Tools\MSVC\14.41.34120\bin\HostX64\x64" -x cu
-I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\include"
-I"E:\repository\vcpkg\installed\x64-windows\include" -I"C:\Program
Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\include" -G --keep-dir
CompilerIdCUDA\x64\Debug -maxrregcount=0 --machine 64 --compile -cudart
static -v -g -D_MBCS -Xcompiler "/EHsc /W0 /nologo /Od /FS /Zi /RTC1 /MDd "
-Xcompiler "/FdDebug\vc143.pdb" -o
E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA\x64\Debug\CMakeCUDACompilerId.cu.obj
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CMakeCUDACompilerId.cu""
exited with code 2.
[E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj]
Done Building Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(CudaBuildCore target(s)) -- FAILED.
Done Building Project
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(default targets) -- FAILED.
Build FAILED.
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(default target) (1) ->
"E:\repository\onnxruntime\build\Windows\Debug\CMakeFiles\3.28.0-rc2\CompilerIdCUDA\CompilerIdCUDA.vcxproj"
(CudaBuildCore target) (1:2) ->
(CudaBuildCore target) ->
Time Elapsed 00:00:00.68
Call Stack (most recent call first):
C:/Program Files/CMake/share/cmake-3.28/Modules/CMakeDetermineCompilerId.cmake:8 (CMAKE_DETERMINE_COMPILER_ID_BUILD)
C:/Program Files/CMake/share/cmake-3.28/Modules/CMakeDetermineCompilerId.cmake:53 (__determine_compiler_id_test)
C:/Program Files/CMake/share/cmake-3.28/Modules/CMakeDetermineCUDACompiler.cmake:135 (CMAKE_DETERMINE_COMPILER_ID)
CMakeLists.txt:770 (enable_language)
-- Configuring incomplete, errors occurred!
Traceback (most recent call last):
File "E:\repository\onnxruntime\tools\ci_build\build.py", line 3019, in
sys.exit(main())
^^^^^^
File "E:\repository\onnxruntime\tools\ci_build\build.py", line 2882, in main
generate_build_tree(
File "E:\repository\onnxruntime\tools\ci_build\build.py", line 1711, in generate_build_tree
run_subprocess(
File "E:\repository\onnxruntime\tools\ci_build\build.py", line 868, in run_subprocess
return run(*args, cwd=cwd, capture_stdout=capture_stdout, shell=shell, env=my_env)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\repository\onnxruntime\tools\python\util\run.py", line 49, in run
completed_process = subprocess.run(
^^^^^^^^^^^^^^^
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_3.11.2544.0_x64__qbz5n2kfra8p0\Lib\subprocess.py", line 571, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['C:\Program Files\CMake\bin\cmake.EXE', 'E:\repository\onnxruntime\cmake', '-Donnxruntime_RUN_ONNX_TESTS=OFF', '-Donnxruntime_GENERATE_TEST_REPORTS=ON', '-DPython_EXECUTABLE=C:\Users\Zbook\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\python.exe', '-DPYTHON_EXECUTABLE=C:\Users\Zbook\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\python.exe', '-Donnxruntime_USE_VCPKG=OFF', '-Donnxruntime_USE_MIMALLOC=OFF', '-Donnxruntime_ENABLE_PYTHON=OFF', '-Donnxruntime_BUILD_CSHARP=OFF', '-Donnxruntime_BUILD_JAVA=OFF', '-Donnxruntime_BUILD_NODEJS=OFF', '-Donnxruntime_BUILD_OBJC=OFF', '-Donnxruntime_BUILD_SHARED_LIB=OFF', '-Donnxruntime_BUILD_APPLE_FRAMEWORK=OFF', '-Donnxruntime_USE_DNNL=OFF', '-Donnxruntime_USE_NNAPI_BUILTIN=OFF', '-Donnxruntime_USE_VSINPU=OFF', '-Donnxruntime_USE_RKNPU=OFF', '-Donnxruntime_ENABLE_MICROSOFT_INTERNAL=OFF', '-Donnxruntime_USE_VITISAI=OFF', '-Donnxruntime_USE_TENSORRT=ON', '-Donnxruntime_USE_TENSORRT_BUILTIN_PARSER=ON', '-Donnxruntime_USE_MIGRAPHX=OFF', '-Donnxruntime_DISABLE_CONTRIB_OPS=OFF', '-Donnxruntime_DISABLE_ML_OPS=OFF', '-Donnxruntime_DISABLE_RTTI=OFF', '-Donnxruntime_DISABLE_EXCEPTIONS=OFF', '-Donnxruntime_MINIMAL_BUILD=OFF', '-Donnxruntime_EXTENDED_MINIMAL_BUILD=OFF', '-Donnxruntime_MINIMAL_BUILD_CUSTOM_OPS=OFF', '-Donnxruntime_REDUCED_OPS_BUILD=OFF', '-Donnxruntime_USE_DML=OFF', '-Donnxruntime_USE_WINML=OFF', '-Donnxruntime_BUILD_MS_EXPERIMENTAL_OPS=OFF', '-Donnxruntime_USE_TELEMETRY=OFF', '-Donnxruntime_ENABLE_LTO=OFF', '-Donnxruntime_USE_ACL=OFF', '-Donnxruntime_USE_ARMNN=OFF', '-Donnxruntime_ARMNN_RELU_USE_CPU=ON', '-Donnxruntime_ARMNN_BN_USE_CPU=ON', '-Donnxruntime_USE_JSEP=OFF', '-Donnxruntime_USE_WEBGPU=OFF', '-Donnxruntime_USE_EXTERNAL_DAWN=OFF', '-Donnxruntime_ENABLE_NVTX_PROFILE=OFF', '-Donnxruntime_ENABLE_TRAINING=OFF', '-Donnxruntime_ENABLE_TRAINING_OPS=OFF', '-Donnxruntime_ENABLE_TRAINING_APIS=OFF', '-Donnxruntime_ENABLE_CPU_FP16_OPS=OFF', '-Donnxruntime_USE_NCCL=OFF', '-Donnxruntime_BUILD_BENCHMARKS=OFF', '-Donnxruntime_USE_ROCM=OFF', '-Donnxruntime_GCOV_COVERAGE=OFF', '-Donnxruntime_USE_MPI=OFF', '-Donnxruntime_ENABLE_MEMORY_PROFILE=OFF', '-Donnxruntime_ENABLE_CUDA_LINE_NUMBER_INFO=OFF', '-Donnxruntime_USE_CUDA_NHWC_OPS=ON', '-Donnxruntime_BUILD_WEBASSEMBLY_STATIC_LIB=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_EXCEPTION_CATCHING=ON', '-Donnxruntime_ENABLE_WEBASSEMBLY_API_EXCEPTION_CATCHING=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_EXCEPTION_THROWING=ON', '-Donnxruntime_WEBASSEMBLY_RUN_TESTS_IN_BROWSER=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_THREADS=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_MEMORY64=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_DEBUG_INFO=OFF', '-Donnxruntime_ENABLE_WEBASSEMBLY_PROFILING=OFF', '-Donnxruntime_ENABLE_LAZY_TENSOR=OFF', '-Donnxruntime_ENABLE_EXTERNAL_CUSTOM_OP_SCHEMAS=OFF', '-Donnxruntime_ENABLE_CUDA_PROFILING=OFF', '-Donnxruntime_ENABLE_ROCM_PROFILING=OFF', '-Donnxruntime_USE_XNNPACK=OFF', '-Donnxruntime_USE_WEBNN=OFF', '-Donnxruntime_USE_CANN=OFF', '-Donnxruntime_USE_TRITON_KERNEL=OFF', '-Donnxruntime_DISABLE_FLOAT8_TYPES=OFF', '-Donnxruntime_DISABLE_SPARSE_TENSORS=OFF', '-Donnxruntime_DISABLE_OPTIONAL_TYPE=OFF', '-Donnxruntime_CUDA_MINIMAL=OFF', '-Donnxruntime_NVCC_THREADS=8', '-DCMAKE_CUDA_COMPILER=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2/bin/nvcc', '-Donnxruntime_TENSORRT_HOME=E:\Libraries\TensorRT-10.5.0.18', '-DCMAKE_VS_GLOBALS=UseMultiToolTask=true;EnforceProcessCountAcrossBuilds=true', '-DCMAKE_TLS_VERIFY=ON', '-DFETCHCONTENT_QUIET=OFF', '-Donnxruntime_USE_CUDA=ON', '-Donnxruntime_CUDA_HOME=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2', '-Donnxruntime_CUDNN_HOME=C:\Program Files\NVIDIA\CUDNN\v8.9', '-DONNX_USE_MSVC_STATIC_RUNTIME=OFF', '-Dprotobuf_MSVC_STATIC_RUNTIME=OFF', '-DABSL_MSVC_STATIC_RUNTIME=OFF', '-Dgtest_force_shared_crt=ON', '-DCMAKE_MSVC_DEBUG_INFORMATION_FORMAT=ProgramDatabase', '-A', 'x64', '-T', 'host=x64,cuda=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2', '-G', 'Visual Studio 17 2022', '-DCMAKE_CUDA_FLAGS_INIT=-allow-unsupported-compiler', '-DCMAKE_BUILD_TYPE=Debug', '-DCMAKE_PREFIX_PATH=E:\repository\onnxruntime\\build\Windows/Debug/installed']' returned non-zero exit status 1.
Visual Studio Version
2022
GCC / Compiler Version
No response
The text was updated successfully, but these errors were encountered: