Closed bonuschild closed 2 months ago
Code Llama runs on the GPU if you setup the codellama repository correctly. You have to install pytorch w/ CUDA support.
I'll close this issue since it has been so long and this probably answers your question. Let me know if you'd like to reopen it.
I saw that you mock
llama.cpp
but I still have gpu resources, event I also have enough cpu & RAM.Just want to figure out it's right scene to deploying.