You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Request for digitally signed Windows CUDA DLLs — Smart App Control blocking llama-cpp-python
#188
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Hello,
I'm using your llama-cpp-python CUDA builds with ComfyUI on Windows 11, Python 3.13, CUDA 13.0, and an NVIDIA RTX 4060 Ti.
Windows Smart App Control is blocking
ggml-base.dllbecause it is not digitally signed.Windows Code Integrity reports event IDs 3077 and 3033, and PowerShell's
Get-AuthenticodeSignatureconfirms the file's status isNotSigned.I also checked the newer v0.4.5 CUDA 13.0 wheel, but its
ggml-base.dllis unsigned as well.Would it be possible to provide Windows CUDA builds with valid Authenticode signatures on the included DLLs?
I'd like to continue using the GGUF models locally without disabling Windows Smart App Control.
Thank you for your work on this project!
All reactions