# Pip install on Google Collab **URL:** \ **Category:** Beginners\ **Created:** [May 19, 2025, 4:20am UTC](https://discuss.huggingface.co/t/pip-install-on-google-collab/155822 "2025-05-19T04:20:44Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![brainweaver](https://avatars.discourse-cdn.com/v4/letter/b/8e7dd6/32.png) [@brainweaver](https://discuss.huggingface.co/u/brainweaver)\ **Post date:** [May 19, 2025, 4:20am UTC](https://discuss.huggingface.co/t/pip-install-on-google-collab/155822/1 "2025-05-19T04:20:44Z")
!CMAKE\_ARGS=“-DLLAMA\_CUBLAS=on” FORCE\_CMAKE=1 pip install llama-cpp-python==0.1.85 --force-reinstall --no-cache-dir -q I get the following error - ``` ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.8/1.8 MB 46.3 MB/s eta 0:00:00 ``` Installing build dependencies … done Getting requirements to build wheel … done Preparing metadata (pyproject.toml) … done ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.0/62.0 kB 140.5 MB/s eta 0:00:00 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.5/45.5 kB 297.1 MB/s eta 0:00:00 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.8/16.8 MB 200.6 MB/s eta 0:00:00 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.8/45.8 kB 235.6 MB/s eta 0:00:00 Building wheel for llama-cpp-python (pyproject.toml) … done ERROR: pip’s dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. numba 0.60.0 requires numpy\<2.1,\>=1.22, but you have numpy 2.2.6 which is incompatible. tensorflow 2.18.0 requires numpy\<2.1.0,\>=1.26.0, but you have numpy 2.2.6 which is incompatible. torch 2.6.0+cu124 requires nvidia-cublas-cu12==12.4.5.8; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cublas-cu12 12.5.3.2 which is incompatible. torch 2.6.0+cu124 requires nvidia-cuda-cupti-cu12==12.4.127; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cuda-cupti-cu12 12.5.82 which is incompatible. torch 2.6.0+cu124 requires nvidia-cuda-nvrtc-cu12==12.4.127; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cuda-nvrtc-cu12 12.5.82 which is incompatible. torch 2.6.0+cu124 requires nvidia-cuda-runtime-cu12==12.4.127; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cuda-runtime-cu12 12.5.82 which is incompatible. torch 2.6.0+cu124 requires nvidia-cudnn-cu12==9.1.0.70; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cudnn-cu12 9.3.0.75 which is incompatible. torch 2.6.0+cu124 requires nvidia-cufft-cu12==11.2.1.3; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cufft-cu12 11.2.3.61 which is incompatible. torch 2.6.0+cu124 requires nvidia-curand-cu12==10.3.5.147; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-curand-cu12 10.3.6.82 which is incompatible. torch 2.6.0+cu124 requires nvidia-cusolver-cu12==11.6.1.9; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cusolver-cu12 11.6.3.83 which is incompatible. torch 2.6.0+cu124 requires nvidia-cusparse-cu12==12.3.1.170; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-cusparse-cu12 12.5.1.3 which is incompatible. torch 2.6.0+cu124 requires nvidia-nvjitlink-cu12==12.4.127; platform\_system == “Linux” and platform\_machine == “x86\_64”, but you have nvidia-nvjitlink-cu12 12.5.82 which is incompatible. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [May 19, 2025, 4:35am UTC](https://discuss.huggingface.co/t/pip-install-on-google-collab/155822/2 "2025-05-19T04:35:57Z")
Hmm… ```auto !CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --no-cache-dir -q ``` or ```auto !CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.85 --force-reinstall --no-cache-dir -q --no-deps ``` ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [May 19, 2025, 4:41am UTC](https://discuss.huggingface.co/t/pip-install-on-google-collab/155822/3 "2025-05-19T04:41:33Z")
Also, the official llama-cpp-python seems to have broken CUDA build settings, so you may want to use the build wheels from the following repository. > **[GitHub - JamePeng/llama-cpp-python: Python bindings for llama.cpp](https://github.com/JamePeng/llama-cpp-python)** > > Python bindings for llama.cpp