Tidux
Tidux
All it needs is M-chip support for the AI backend(s?) under Linux in the `exo` tool. The rest I could put together at the sysadmin level - Dockerfiles, Kubernetes manifests,...
It looks like mlx is Metal/MacOS only for now so this remains on hold until that changes.
Maybe this is a usecase for using a WASM runtime instead of native binaries? There's a defined WASM spec and sandbox, so the hash enclosure would only have to cover...
> Curious, why so? Linux lets you pass GPU devices in to a container, even in a Kubernetes cluster. This means rather than running something like `ansible arm_mac_cluster -a "exo...
Have you tried running in Kubernetes? Tailscale has an Operator that makes it easy to expose a service to the tailnet.
I'm not sure if Ramalama uses a different REST API but it's a similar tool and would also be appreciated. https://github.com/containers/ramalama
Gtk, and thus Firefox and Chrome, will be going Wayland-only starting in Gtk6. https://www.osnews.com/story/141670/gtk-announces-x11-deprecation-new-android-backend-and-much-more/