-- CUDA Toolkit found

(CUDA125-py312) PS E:\llama-cpp-python\build> cmake -G "Visual Studio 17 2022" -A x64 `
>> -DCUDA_TOOLKIT_ROOT_DIR="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5" `
>> -DCMAKE_CUDA_COMPILER="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5/bin/nvcc.exe" `
>> -DCMAKE_CUDA_ARCHITECTURES="89" `
>> -DGGML_CUDA=ON ..
-- Selecting Windows SDK version 10.0.22621.0 to target Windows 10.0.26100.
-- The C compiler identification is MSVC 19.43.34808.0
-- The CXX compiler identification is MSVC 19.43.34808.0
-- Detecting C compiler ABI info
-- Detecting C compiler ABI info - done
-- Check for working C compiler: C:/Program Files/Microsoft Visual Studio/2022/Professional/VC/Tools/MSVC/14.43.34808/bin/Hostx64/x64/cl.exe - skipped
-- Detecting C compile features
-- Detecting C compile features - done
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Check for working CXX compiler: C:/Program Files/Microsoft Visual Studio/2022/Professional/VC/Tools/MSVC/14.43.34808/bin/Hostx64/x64/cl.exe - skipped
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Found Git: C:/Program Files/Git/cmd/git.exe (found version "2.47.1.windows.2")
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - not found
-- Found Threads: TRUE
-- Warning: ccache not found - consider installing it for faster compilation or disable this warning with GGML_CCACHE=OFF
-- CMAKE_SYSTEM_PROCESSOR: AMD64
-- CMAKE_GENERATOR_PLATFORM: x64
-- Including CPU backend
-- Found OpenMP_C: -openmp (found version "2.0")
-- Found OpenMP_CXX: -openmp (found version "2.0")
-- Found OpenMP: TRUE (found version "2.0")
-- x86 detected
-- Performing Test HAS_AVX_1
-- Performing Test HAS_AVX_1 - Success
-- Performing Test HAS_AVX2_1
-- Performing Test HAS_AVX2_1 - Success
-- Performing Test HAS_FMA_1
-- Performing Test HAS_FMA_1 - Success
-- Performing Test HAS_AVX512_1
-- Performing Test HAS_AVX512_1 - Failed
-- Performing Test HAS_AVX512_2
-- Performing Test HAS_AVX512_2 - Failed
-- Adding CPU backend variant ggml-cpu: /arch:AVX2 GGML_AVX2;GGML_FMA;GGML_F16C
-- Found CUDAToolkit: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5/include (found version "12.5.82")
-- CUDA Toolkit found
-- Using CUDA architectures: 89
CMake Error at D:/software/Minipy312/envs/CUDA125-py312/Lib/site-packages/cmake/data/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:614 (message):
No CUDA toolset found.
Call Stack (most recent call first):
D:/software/Minipy312/envs/CUDA125-py312/Lib/site-packages/cmake/data/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:8 (CMAKE_DETERMINE_COMPILER_ID_BUILD)
D:/software/Minipy312/envs/CUDA125-py312/Lib/site-packages/cmake/data/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:53 (__determine_compiler_id_test)
D:/software/Minipy312/envs/CUDA125-py312/Lib/site-packages/cmake/data/share/cmake-3.31/Modules/CMakeDetermineCUDACompiler.cmake:131 (CMAKE_DETERMINE_COMPILER_ID)
vendor/llama.cpp/ggml/src/ggml-cuda/CMakeLists.txt:25 (enable_language)

-------------------------------

补充信息：
E:\llama-cpp-python>where nvcc.exe
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.5\bin\nvcc.exe

E:\llama-cpp-python>nvcc.exe --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Jun__6_03:03:05_Pacific_Daylight_Time_2024
Cuda compilation tools, release 12.5, V12.5.82
Build cuda_12.5.r12.5/compiler.34385749_0

git clone --recurse-submodules https://github.com/abetlen/llama-cpp-python.git

---------------------
E:\llama-cpp-python\build>set CXXFLAGS="/std:c++17"
E:\llama-cpp-python\build>cmake -G "Visual Studio 17 2022" -A x64 ^
More? -DCUDA_TOOLKIT_ROOT_DIR="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5" ^
More? -DCMAKE_CUDA_COMPILER="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5/bin/nvcc.exe" ^
More? -DCMAKE_CUDA_ARCHITECTURES="89" ^
More? -DGGML_CUDA=ON ..
-- Selecting Windows SDK version 10.0.22621.0 to target Windows 10.0.26100.
-- The C compiler identification is MSVC 19.43.34808.0
-- The CXX compiler identification is MSVC 19.43.34808.0
-- Detecting C compiler ABI info
-- Detecting C compiler ABI info - done
-- Check for working C compiler: C:/Program Files/Microsoft Visual Studio/2022/Professional/VC/Tools/MSVC/14.43.34808/bin/Hostx64/x64/cl.exe - skipped
-- Detecting C compile features
-- Detecting C compile features - done
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Check for working CXX compiler: C:/Program Files/Microsoft Visual Studio/2022/Professional/VC/Tools/MSVC/14.43.34808/bin/Hostx64/x64/cl.exe - skipped
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Found Git: C:/Program Files/Git/cmd/git.exe (found version "2.47.1.windows.2")
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - not found
-- Found Threads: TRUE
-- Warning: ccache not found - consider installing it for faster compilation or disable this warning with GGML_CCACHE=OFF
-- CMAKE_SYSTEM_PROCESSOR: AMD64
-- CMAKE_GENERATOR_PLATFORM: x64
-- Including CPU backend
-- Found OpenMP_C: -openmp (found version "2.0")
-- Found OpenMP_CXX: -openmp (found version "2.0")
-- Found OpenMP: TRUE (found version "2.0")
-- x86 detected
-- Performing Test HAS_AVX_1
-- Performing Test HAS_AVX_1 - Success
-- Performing Test HAS_AVX2_1
-- Performing Test HAS_AVX2_1 - Success
-- Performing Test HAS_FMA_1
-- Performing Test HAS_FMA_1 - Success
-- Performing Test HAS_AVX512_1
-- Performing Test HAS_AVX512_1 - Failed
-- Performing Test HAS_AVX512_2
-- Performing Test HAS_AVX512_2 - Failed
-- Adding CPU backend variant ggml-cpu: /arch:AVX2 GGML_AVX2;GGML_FMA;GGML_F16C
-- Found CUDAToolkit: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5/include (found version "12.5.82")
-- CUDA Toolkit found
-- Using CUDA architectures: 89
CMake Error at D:/Program Files/CMake/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:614 (message):
No CUDA toolset found.
Call Stack (most recent call first):
D:/Program Files/CMake/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:8 (CMAKE_DETERMINE_COMPILER_ID_BUILD)
D:/Program Files/CMake/share/cmake-3.31/Modules/CMakeDetermineCompilerId.cmake:53 (__determine_compiler_id_test)
D:/Program Files/CMake/share/cmake-3.31/Modules/CMakeDetermineCUDACompiler.cmake:131 (CMAKE_DETERMINE_COMPILER_ID)
vendor/llama.cpp/ggml/src/ggml-cuda/CMakeLists.txt:25 (enable_language)

-- Configuring incomplete, errors occurred!