Heading to Brussels for #FOSDEM26 (Jan 31- Feb 1)? Want to learn about Docker Model Runner and other AI offerings at Docker? Dorin and I will be speaking in the AI Plumbers DevRoom on Saturday and hope to see you there
Eric Curtin
- 270 Followers
- 71 Following
- 507 Posts
Docker Engineer working in AI
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.
Weird World Of Wayland Compositors On MacOS
Apple GPU support for vLLM? Monorepos vs microrepos?
Recently we did a webinar on Docker Model Runner. I prepared a slide on my take of when to use llama.cpp and when to use vLLM. Here is what I came up with (and I feel Edge kinda fits in the middle, there are use cases for both), but I am curious what do people think?
This feature in the upcoming systemd release started from the efforts of the Red Hat In-Vehicle OS team Brian Masney Alexander Calhoun . Probably just less than 2 years in the making, but it finally made it! Thanks to Francesco Valla for driving it to completion.
"in certain fixed-function usecases it might make sense to load modules via this infrastructure during boot"
Often in Automotive, we know exactly the hardware and software stack that is to be deployed and there is little plug and play from the boot perspective. Bypassing udevd and loading boot-time critical kernel modules early in parallel can lead to significant boot speedups. And by starting udevd later, we still get the benefits of udev.
One myth about systemd is that it's too fat to boot quickly, if we build up systemd from scratch starting with just the systemd binary itself, we can start critical boot services in milliseconds, as fast as any init system we would write from scratch in a few lines of C, the core of systemd is lightweight.
https://mastodon.social/users/pid_eins/statuses/115620451885638963
Emile "iMil" 
HeitorWOAAAA!!!! #smolBSD with libkrun on aarch64!! By the one and only @slp ❤️
https://x.com/slpnix/status/1984400857077572027?t=h59EGz3mWrbKtTDdlq6fOA&s=19
Join Us in Rebooting the Docker Model Runner Community!
https://news.ycombinator.com/item?id=45579368
https://www.docker.com/blog/rebooting-model-runner-community/
Check out the latest on Docker Model Runner! And we would love your contributions. Star, fork, and contribute to the project. Let's build the future of AI together! #Docker #OpenSource #AI #LLM #inferencing #llamacpp
GitHub: https://github.com/docker/model-runner
Blog Post: https://www.linkedin.com/pulse/top-docker-model-runner-features-developers-love-whats-next-docker-1axwf/?trackingId=mB2AhjTlqJsroeyJ0CffVg%3D%3D
After many years of maintaining inotify-tools we finally have a logo:
