Fabric
Fabric copied to clipboard
Ollama not utalizing gpu through fabric
What is your question?
After reading the documentation, I am still not clear how to get fabric to use the GPU through ollama. I am able to call ollama by itself and see my GPU being used. however whenever I run a command through fabric (using Ollama) it seems to use the CPU. I am running it on Ubuntu. I have tried a few different things but cant seem to get it to work. It wouldnt be much of an issue except for the fact that when the CPU is utalized the replies take quite some time to come back