Prerequisites

Please answer the following questions for yourself before submitting an issue.

[X] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
[X] I carefully followed the README.md.
[X] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
[X] I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

Correct installation of llama-cpp-python.

Current Behavior

I was upgrading to version 0.3.2 and during the upgrade it gave me a series of errors and the build failed. I installed version 3.0.1 without any problems.

Environment and Context

Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.

Physical (or virtual) hardware you are using, e.g. for Linux:

$ RTX 3060 LAPTOP 6GB

Operating System:

$ Windows 11

SDK version:

$ python3 --3.12

Failure Information (for bugs)

Please help provide information about the failure if this is a bug. If it is not a bug, please remove the rest of this template.

Steps to Reproduce

Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.

step 1: Install llama-cpp-python 0.3.1 on Windows with CUDA support

step 2: Update to version 0.3.2 with this command:

$env:CMAKE_ARGS = "-DGGML_CUDA=on"
>> pip install llama-cpp-python --upgrade --force-reinstall --no-cache-dir

Failure Logs

      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\ALL_BUILD.vcxproj" (destinazione predefinita) (1) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\examples\llava\llava.vcxproj" (destinazione predefinita) (4) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml.vcxproj" (destinazione predefinita) (5) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione predefinita) (9) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione: CudaBuildCore) (9:67) ->
        c1xx : fatal error C1083: Cannot open source file: 'C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f16-instance-hs256-f16-f16.cu': No such file or directory [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]
        C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 12.4.targets(799,9): error MSB3721: uscita dal comando ""C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe"  --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:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\.." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\..\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include"     --keep-dir ggml-cuda\x64\Release  -maxrregcount=0   --machine 64 --compile -cudart static --generate-code=arch=compute_52,code=[compute_52,sm_52] --generate-code=arch=compute_61,code=[compute_61,sm_61] --generate-code=arch=compute_70,code=[compute_70,sm_70] --generate-code=arch=compute_75,code=[compute_75,sm_75] -Xcompiler="/EHsc -Ob2"   -D_WINDOWS -DNDEBUG -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -D_CRT_SECURE_NO_WARNINGS -DGGML_SCHED_MAX_COPIES=4 -D_XOPEN_SOURCE=600 -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_USE_GRAPHS -DGGML_SHARED -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -D_WINDLL -D_MBCS -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -Xcompiler "/EHsc /W1 /nologo /O2 /FS   /MD " -Xcompiler "/Fdggml-cuda.dir\Release\vc143.pdb" -o ggml-cuda.dir\Release\fattn-vec-f16-instance-hs256-f16-f16.obj "C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f16-instance-hs256-f16-f16.cu"" con codice 2. [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]

      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\ALL_BUILD.vcxproj" (destinazione predefinita) (1) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\examples\llava\llava.vcxproj" (destinazione predefinita) (4) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml.vcxproj" (destinazione predefinita) (5) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione predefinita) (9) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione: CudaBuildCore) (9:68) ->
        c1xx : fatal error C1083: Cannot open source file: 'C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f16-instance-hs64-f16-f16.cu': No such file or directory [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]
        C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 12.4.targets(799,9): error MSB3721: uscita dal comando ""C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe"  --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:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\.." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\..\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include"     --keep-dir ggml-cuda\x64\Release  -maxrregcount=0   --machine 64 --compile -cudart static --generate-code=arch=compute_52,code=[compute_52,sm_52] --generate-code=arch=compute_61,code=[compute_61,sm_61] --generate-code=arch=compute_70,code=[compute_70,sm_70] --generate-code=arch=compute_75,code=[compute_75,sm_75] -Xcompiler="/EHsc -Ob2"   -D_WINDOWS -DNDEBUG -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -D_CRT_SECURE_NO_WARNINGS -DGGML_SCHED_MAX_COPIES=4 -D_XOPEN_SOURCE=600 -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_USE_GRAPHS -DGGML_SHARED -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -D_WINDLL -D_MBCS -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -Xcompiler "/EHsc /W1 /nologo /O2 /FS   /MD " -Xcompiler "/Fdggml-cuda.dir\Release\vc143.pdb" -o ggml-cuda.dir\Release\fattn-vec-f16-instance-hs64-f16-f16.obj "C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f16-instance-hs64-f16-f16.cu"" con codice 2. [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]

      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\ALL_BUILD.vcxproj" (destinazione predefinita) (1) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\examples\llava\llava.vcxproj" (destinazione predefinita) (4) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml.vcxproj" (destinazione predefinita) (5) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione predefinita) (9) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione: CudaBuildCore) (9:69) ->
        c1xx : fatal error C1083: Cannot open source file: 'C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs128-f16-f16.cu': No such file or directory [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]
        C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 12.4.targets(799,9): error MSB3721: uscita dal comando ""C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe"  --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:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\.." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\..\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include"     --keep-dir ggml-cuda\x64\Release  -maxrregcount=0   --machine 64 --compile -cudart static --generate-code=arch=compute_52,code=[compute_52,sm_52] --generate-code=arch=compute_61,code=[compute_61,sm_61] --generate-code=arch=compute_70,code=[compute_70,sm_70] --generate-code=arch=compute_75,code=[compute_75,sm_75] -Xcompiler="/EHsc -Ob2"   -D_WINDOWS -DNDEBUG -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -D_CRT_SECURE_NO_WARNINGS -DGGML_SCHED_MAX_COPIES=4 -D_XOPEN_SOURCE=600 -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_USE_GRAPHS -DGGML_SHARED -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -D_WINDLL -D_MBCS -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -Xcompiler "/EHsc /W1 /nologo /O2 /FS   /MD " -Xcompiler "/Fdggml-cuda.dir\Release\vc143.pdb" -o ggml-cuda.dir\Release\fattn-vec-f32-instance-hs128-f16-f16.obj "C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs128-f16-f16.cu"" con codice 2. [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]

      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\ALL_BUILD.vcxproj" (destinazione predefinita) (1) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\examples\llava\llava.vcxproj" (destinazione predefinita) (4) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml.vcxproj" (destinazione predefinita) (5) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione predefinita) (9) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione: CudaBuildCore) (9:70) ->
        c1xx : fatal error C1083: Cannot open source file: 'C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs256-f16-f16.cu': No such file or directory [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]
        C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 12.4.targets(799,9): error MSB3721: uscita dal comando ""C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe"  --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:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\.." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\..\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include"     --keep-dir ggml-cuda\x64\Release  -maxrregcount=0   --machine 64 --compile -cudart static --generate-code=arch=compute_52,code=[compute_52,sm_52] --generate-code=arch=compute_61,code=[compute_61,sm_61] --generate-code=arch=compute_70,code=[compute_70,sm_70] --generate-code=arch=compute_75,code=[compute_75,sm_75] -Xcompiler="/EHsc -Ob2"   -D_WINDOWS -DNDEBUG -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -D_CRT_SECURE_NO_WARNINGS -DGGML_SCHED_MAX_COPIES=4 -D_XOPEN_SOURCE=600 -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_USE_GRAPHS -DGGML_SHARED -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -D_WINDLL -D_MBCS -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -Xcompiler "/EHsc /W1 /nologo /O2 /FS   /MD " -Xcompiler "/Fdggml-cuda.dir\Release\vc143.pdb" -o ggml-cuda.dir\Release\fattn-vec-f32-instance-hs256-f16-f16.obj "C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs256-f16-f16.cu"" con codice 2. [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]

      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\ALL_BUILD.vcxproj" (destinazione predefinita) (1) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\examples\llava\llava.vcxproj" (destinazione predefinita) (4) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml.vcxproj" (destinazione predefinita) (5) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione predefinita) (9) ->
      "C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj" (destinazione: CudaBuildCore) (9:71) ->
        c1xx : fatal error C1083: Cannot open source file: 'C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs64-f16-f16.cu': No such file or directory [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]
        C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\BuildCustomizations\CUDA 12.4.targets(799,9): error MSB3721: uscita dal comando ""C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exe"  --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:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\.." -I"C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\..\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include"     --keep-dir ggml-cuda\x64\Release  -maxrregcount=0   --machine 64 --compile -cudart static --generate-code=arch=compute_52,code=[compute_52,sm_52] --generate-code=arch=compute_61,code=[compute_61,sm_61] --generate-code=arch=compute_70,code=[compute_70,sm_70] --generate-code=arch=compute_75,code=[compute_75,sm_75] -Xcompiler="/EHsc -Ob2"   -D_WINDOWS -DNDEBUG -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -D_CRT_SECURE_NO_WARNINGS -DGGML_SCHED_MAX_COPIES=4 -D_XOPEN_SOURCE=600 -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_USE_GRAPHS -DGGML_SHARED -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -D_WINDLL -D_MBCS -D"CMAKE_INTDIR=\"Release\"" -Dggml_cuda_EXPORTS -Xcompiler "/EHsc /W1 /nologo /O2 /FS   /MD " -Xcompiler "/Fdggml-cuda.dir\Release\vc143.pdb" -o ggml-cuda.dir\Release\fattn-vec-f32-instance-hs64-f16-f16.obj "C:\Users\paolo\AppData\Local\Temp\pip-install-81_4wj0i\llama-cpp-python_f216333ad4b04739a389898d9231279d\vendor\llama.cpp\ggml\src\ggml-cuda\template-instances\fattn-vec-f32-instance-hs64-f16-f16.cu"" con codice 2. [C:\Users\paolo\AppData\Local\Temp\tmpbixkztt6\build\vendor\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.vcxproj]

          Avvisi: 10
          Errori: 62

      Tempo trascorso 00:15:44.18

      *** CMake build failed
      [end of output]
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for llama-cpp-python
Failed to build llama-cpp-python
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python)

I posted only the last part of the failure logs because it was too long, but the errors are the same ( C1083 and MSB3721).

P.S. My mistake, I had mistaken the order of the arguments of pip install.

abetlen / llama-cpp-python

Error when update to 0.3.2 #1837