Eric Curtin

@[email protected]
269 Followers
71 Following
510 Posts
Docker Engineer working in AI
Eric CurtinApr 2

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.

GitHub - ericcurtin/inferrs: A TurboQuant inference engine

A TurboQuant inference engine. Contribute to ericcurtin/inferrs development by creating an account on GitHub.

GitHub
Eric CurtinMar 31
Kevin WittekMar 31
Very happy to share, what our team at #docker has been cooking for the last months. It is our evolution of the `docker sandbox` command, now available as a standalone binary `sbx`, a modern Docker take on AI agent sandboxing, check it out at https://docs.docker.com/ai/sandboxes
Docker Sandboxes

Run AI coding agents in isolated environments

Docker Documentation
Show threadEric CurtinMar 26

@taoeffect @fedora this one from here is the correct one, please someone open a pr to change the docs (I'm on a phone):

https://asahilinux.org/

Asahi Linux

Show threadEric CurtinMar 16
@lina contributions welcome to Docker Model Runner FWIW, this is one of the things we are trying to do
Show threadEric CurtinMar 6
@chandlerc #fixgmail
Show threadEric CurtinFeb 25
@hrw @argv_minus_one I have no idea FWIW, I don't use FEX just something I saw around the place.
Show threadEric CurtinFeb 24
@hrw I think I saw somebody in Asahi world mentioning bugs in latest Fedora with Fex, didn't read thoroughly or anything though
Show threadEric CurtinFeb 7
@McNight contributions welcome also 😊
Show threadEric CurtinJan 28
@slp if someone did port this or something like the complete Qemu UI or wayoa into libkrun directly, would that be accepted into that repo? Or better as a seperate repo?
Show threadEric CurtinJan 28
@slp the goal was to ultimately use with libkrun of course😊