llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard

Published 20 hours ago • verified publisher icon ggml-org

Metal doesn't work in x86 macos

Open qq249356520 opened this issue 10 months ago • 1 comments

MacOS CPU:Intel Core i7 GPU:AMD Radeon Pro 5500 XT 8 GB memory:32G

When I open metal in this mac to run " ./main -m "./Meta-Llama-3-8B.Q4_0.gguf" -p "Hi you how are you" -n 50 -e -ngl 33 -t 4 "

the error occured : image

If I close the metal, it worked. How to fix it in X86 cpu?

qq249356520 avatar Apr 29 '24 12:04 qq249356520

Which version of llama.cpp are you using?

The ggml-metal.metal file that's being reported as missing should be in the root of the repo. Make sure you are running the latest version and that it is there.

arnfaldur avatar May 14 '24 23:05 arnfaldur