Our great sponsors
-
Awesome-Rust-MachineLearning
This repository is a list of machine learning libraries written in Rust. It's a compilation of GitHub repositories, blogs, books, movies, discussions, papers, etc. 🦀
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
XNNPACK
High-efficiency floating-point neural network inference operators for mobile, server, and Web
-
There’s an awesome-git list for a bunch of ML rust stuff not sure how up to date it is as well https://github.com/vaaaaanquish/Awesome-Rust-MachineLearning … not mine
Why are you writing your own inference code in C++ or Rust instead of using some kind of established framework like XNNPACK?
The ownership model & borrow checker makes rust a bit of an awkward language in which to write complex data structures like trees and graphs. It can be done - since you can always use raw pointers & unsafe code when you absolutely need to to treat rust like C. But the language fights you, and the community can get a bit moralistic about this sort of thing. The rust nomicon is a fantastic resource for learning the limits of the borrow checker, and where and how to use unsafe code correctly. You will need unsafe less than you think you will, but sometimes you will have no choice.