Daniel J Walsh

I think the stack dump log and the information about your hardware to start. Then we can see what they say.

Since we have had no further feedback, I am going to close this issue. Reopen if this is still a problem with RamaLama.

LGTM

Thanks @chris-reeves

@nalind @flouthoc @giuseppe @mheon @Luap99 @giuseppe PTAL

@chris-reeves Are you still working on this?

@nalind PTAL

Well we need a rebase first, and then we should be able to get it in.

Not sure what you mean? We can currently push models to OCI, do you want to push models to Huggingface and Ollama?

You mean `ramalama serve`, but would love to see a PR to see what you would like.