Asgir
Asgir
I have the same issue. # Description When attempting to set up llama cpp python for GPU support using CUDA toolkit, following the documented steps, the initialization of the llama-cpp...
An update that may help in narrowing this down: Under windows 11: - building llama.cpp with cmake and then installing llama_cpp_python with linked library still causes the issue. - calling...
For me the issue under windows 11 seems to have been resolved with the latest updates (no idea which). Installing via pip with CUDA works fine now: Create conda environment...
Usually nothing, but I tried pandas and it works fine too.