Closed glcraft closed 2 months ago
Minor fixes some common or linux specific code applied in the meantime.
Hold on, llama.cpp doesn't seem to enable the GPU when I load and use the model when I import it in a project.
Ok it now works fine on my custom project 👌
24 - Fix CUDA native build on Windows, so you don't have to rely on Docker
Minor fixes some common or linux specific code applied in the meantime.