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
Would you consider adding official precompiled binaries with Vulkan support for Intel-based macOS machines (using MoltenVK)?
There is a large number of users on macs that use Intel Macs with AMD GPUs that without compiling llama.cpp manually are sentenced to use rather slow CPU mode.
Most of Macs have rather powerful GPUs, and users can't use them for LLMs without compiling directly (most can't do it due to lack of experience with compiling and few guides online are full of errors).
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 maintainers!
Would you consider adding official precompiled binaries with Vulkan support for Intel-based macOS machines (using MoltenVK)?
There is a large number of users on macs that use Intel Macs with AMD GPUs that without compiling llama.cpp manually are sentenced to use rather slow CPU mode.
Most of Macs have rather powerful GPUs, and users can't use them for LLMs without compiling directly (most can't do it due to lack of experience with compiling and few guides online are full of errors).
Beta Was this translation helpful? Give feedback.
All reactions