How about making libtorch a first class citizen without crashes and memory leaks? What happened to the "one tool, one job" philosophy?
As an interesting thought experiment: Should PyTorch be integrated into systemd or should systemd be integrated into PyTorch? Both seem to absorb everything else like a black hole.
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)
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!