

51·
16 days agoLlama.cpp now supports Vulkan, so it doesn’t matter what card you’re using.


Llama.cpp now supports Vulkan, so it doesn’t matter what card you’re using.


I successfully ran local Llama with llama.cpp and an old AMD GPU. I’m not sure why you think there’s no other option.
Want a nice project to spend your resources on? Try working on a PDF viewer that supports verifying signatures, form filling and signing documents.
Stop fucking around with meaningless issues.