Ado012

> I had been facing this problem for a [while](https://github.com/abetlen/llama-cpp-python/issues/1166#issuecomment-2294990187). Just tried again now weeks later and this **worked**: > > ```shell > CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python --force-reinstall --no-cache-dir >...

> are you sure you got the nvcc configurations right? with you can check `which nvcc` or `nvcc --version`. if there is no output : > > you can add...

> I haven't installed cuda toolkit and this worked for me pip install --no-cache-dir llama-cpp-python==0.3.2 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu/ You and the guy above you are you sure you are using the...

Google Colab has updated to CUDA 12.5 so none of the prebuilt wheels work anymore as far as I can see and I haven't been able to figure out how...

> > Google Colab has updated to CUDA 12.5 so none of the prebuilt wheels work anymore as far as I can see and I haven't been able to figure...