When running: cmake -B build -DGGML_CUDA=ON
cmake –build build –config Release(answer originally found here (https://github.com/abetlen/llama-cpp-python/issues/247#issuecomment-1565561039) )
Answer:
you just need to copy all the four files from C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\extras\visual_studio_integration\MSBuildExtensions, and paste them to C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\MSBuild\Microsoft\VC\v160\BuildCustomizations. These paths should be changed to your own.
(For me, my destination directory looks like this: C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\MSBuild\Microsoft\VC\v160\BuildCustomizations
)
Leave a Reply