llama_cpp_python 0.3.16 with CUDA enabled.
Includes Python 3.11 and Python 3.12.sm_75 (RTX 20xx)sm_86 (RTX 30xx)sm_89 (RTX 40xx)sm_120 (RTX 50xx)llama_cpp_python-0.3.16-cp311-cp311-win_amd64.whlllama_cpp_python-0.3.16-cp312-cp312-win_amd64.whl