mlx-lm now supports image inputs with Muse!
I asked Muse to explain a screenshot of the profiler output from its own decode.
Muse explaining Muse. All running locally on two M5 Ultras with mlx ❤️
I was working on some optimization for mlx and noticed that our rmsnorm backward was hitting significantly lower bandwidth than forward. I wrote a small note on why that’s the case and how it could be fixed.