Eric Curtin

> Alright, I've been working on this recently and while `podman artifact pull` can totally be used for the ollama registry, the problem is the registry itself. The registry at...

Another somewhat related thing is we proved: `podman artifact pull docker.io/ai/smollm2` works. But I don't think we put in the effort to connect the dots yet so: `ramalama run docker://docker.io/ai/smollm2`...

> Good luck, the broken registry might be part of the prioritization strategy. Echoing what was said here. There have been pull requests opened in Ollama tool to enhance interop...

I think doing things this way for skopeo `--do-not-ping-registry-v2`, `--accept-ollama-model` sounds fine. From the RamaLama perspective we would continue to do these exceptional things based on if: "ollama://" is prefixed...

@aafeijoo-suse I will test this initrd extensively. An initrd _may_ not be bootable if you remove certain files, it depends on your initrd, your use-case and how you define your...

We added Vulkan support to docker model runner, which will likely solve this issue: https://www.docker.com/blog/docker-model-runner-vulkan-gpu-support/ We've also put effort to putting all our code in one central place to make...

This is a check that has been there at least 10 years: https://github.com/ostreedev/ostree/commit/1e080b9c7370dc6c4e9d95a905d31b4f4dfe83c3 I don't see any immediate issue with removing that check, but @cgwalters is the writer of that...

We should consider talking to docker and ollama about this too

@engelmi PTAL

@ngxson I need an approval here, this is mostly refactoring with some functional changes