friedrich VS tch-rs

For other algorithms, there is not yet a single library to rule them all (linfa might become that at some point) but searching for the algorithm you need on crate.io is likely to give you some results (obligatory plug to Friedrich, my gaussian process implementation).

For me the good reason to use gaussian regression is the fact that you get an uncertainty on the output.

The big downside is that it takes expert knowledge (to design a proper kernel) and a solid implementation (to avoid the various numerical problems they can produce) to apply them to practical problem. Most implementation either break down very quickly or are not flexible enough for my taste.

I have a Rust implementation [0] which tries to help with the flexibility aspect but it is still very far from perfect.

[0]: https://github.com/nestordemeure/friedrich

I wanted to do something like this but then I would miss on proper CUDA acceleration and lose performance compared to using torchlib.

I wrote a forgettable llama implementation for https://github.com/LaurentMazare/tch-rs (pytorch's torchlib rust binding).

I first encountered OCaml's PyTorch bindings because apparently they generate a C wrapper around PyTorch's C++ API, and Rust's PyTorch bindings use OCaml's C wrapper. See: https://github.com/LaurentMazare/tch-rs

You could try looking at the min-GPT example of tch-rs. I'd also strongly suggest watching Karpathy's video to understand what's going on.

If you pefer to see it in code there's a succint gpt implementation here https://github.com/LaurentMazare/tch-rs/blob/main/examples/m...

Rust is fully compatible w/ C bindings, so even Python libraries written in C can be easily set up to work in Rust (and have been). For example, see PyTorch Rust bindings, which actually works faster than in Python because all of the glue code around the C++ API is in Rust instead of Python.

Pytorch

I have looked into this a bit and found some crates which help in loading torchscript models called tch-rs