Did not know executorch existed! That's so cool! I have it on my bucket list to tinker with running LLMs on wearables after I'm a little further along in learning, great to see official tooling for that!
I think this is not about new Pytorch features, although it requires the latest Pytorch and Executorch making me think that some features in pytorch and executorch got extended optimized for this use case?
What makes this cool is that you can use the same model and the same library and apply to server, desktop, laptop and mobile on iOS and Android, with a variety of quantization schemes and other features.
Definitely still some rough edges as I'd expect from any first software release!
It's just a showcase of existing PyTorch features (including libtorch) as an end-to-end example.
On the server-side it uses libtorch, and on mobile, it uses PyTorch's executorch runtime (that's optimized for edge)