Doesn't work for me it seems.

[uorufu]

I can't seem to get llama.cpp build on me windows for some reason. :(

Found this repo and thought it might be what I am looking for. As I tried to do it manually and keep running into errors.

Get this error when trying to run install_llama_cpp.ps1

  CMakeCUDACompilerId.cu

  C:\Program Files\NVIDIA GPU Computing
  Toolkit\CUDA\v12.4\include\crt/host_config.h(170): 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.

  # --error 0x2 --





Call Stack (most recent call first):
  C:/Python/Python313/Lib/site-packages/cmake/data/share/cmake-4.4/Modules/CMakeDetermineCompilerId.cmake:8 (CMAKE_DETERMINE_COMPILER_ID_BUILD)
  C:/Python/Python313/Lib/site-packages/cmake/data/share/cmake-4.4/Modules/CMakeDetermineCompilerId.cmake:53 (__determine_compiler_id_test)
  C:/Python/Python313/Lib/site-packages/cmake/data/share/cmake-4.4/Modules/CMakeDetermineCUDACompiler.cmake:163 (CMAKE_DETERMINE_COMPILER_ID)
  ggml/src/ggml-cuda/CMakeLists.txt:59 (enable_language)


-- Configuring incomplete, errors occurred!
Exception: E:\Text\llama.cpp-installer\install_llama_cpp.ps1:501
Line |
 501 |          throw "$What failed with exit code $LASTEXITCODE."
     |          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     | cmake configure failed with exit code 1.