Another day, another 6ms knocked of Linux boot speed:
Eric Curtin
Docker Engineer working in AI
RE: @vvbudh@climatejustice.social
Genuinely I think many of the systemd haters don't know why they hate systemd, just heard someone else say it and followed along
https://www.youtube.com/watch?v=m061eizaEko
Some points to clarify on wayoa. The Metal rendering, that's for the macOS window. We would expect the Linux application and VMM to use GPU acceleration via KosmicKrisp. https://github.com/ericcurtin/wayoa and https://github.com/ericcurtin/vmm are open to contributions.
The world's first inference server with Gemma 4 and TurboQuant:
brew tap ericcurtin/inferrs
brew install inferrs
inferrs run --turbo-quant google/gemma-4-E2B-it
https://github.com/ericcurtin/inferrs
Gemma 4 and TurboQuant coming to Docker Model Runner soon. Gemma 4 is available on Docker Hub.
With murmurings around the Nvidia/Hugging Face deal, ever wonder if it would be cool if we could pull models from Hugging Face or many other types of model registries. The solution exists and is hiding right under our eyes:
https://llmmanorg.github.io/blog/mirror-hugging-face-models-into-any-oci-registry/
Models are just OCI artifacts.