Skip to content

Conversation

@ajparsons
Copy link

@ajparsons ajparsons commented Oct 24, 2025

I needed to add this DLL for the library to work on my system (possibly to do with a new cuda toolkit version, unclear).

Possibly related to #2070.

If anyone else encounters this, you can work around by adding it before importing:

import os
if "CUDA_PATH" in os.environ:
    os.add_dll_directory(os.path.join(os.environ["CUDA_PATH"], "bin", "x64"))
import llama_cpp
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant