lama cpp

#3
by goodasdgood - opened

C:\Users\ArabTech\Desktop\3\llama.cpp>llama-cli -m C:\Users\ArabTech\Desktop\3\llama-3.1-8b-lexi-uncensored-v2-q8_0.gguf -p "You are a helpful assistant" -cnv -ngl 33
warning: not compiled with GPU offload support, --gpu-layers option will be ignored

it run without gpu
why?

@goodasdgood This is not a model issue but a llama.cpp topic. Check the instructions here for compiling with CUDA support:
https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md

Orenguteng changed discussion status to closed

Sign up or log in to comment