Where can I learn more about SIMD, CPU intrinsics and the like in the context of Rust?

This may not be rust specific, but I am wanting to learn more about these topics in the context of Rust and would appreciate any Rust resources/blogs that deal with this.

I am a machine learning researcher working in NLP, but mostly on the higher level research. I have been tracking the progress of language model implementations on the C++ side lately and have been very impressed with the effort and performance of https://github.com/ggerganov/llama.cpp

I have seen some Rust attempts as well such as https://github.com/Noeda/rllama/ but they are still way behind the C++ ones. This seems like an interesting space to get into.

But there seems to be a lot of optimization and hardware related work in these attempts that I am unfamiliar with including SIMD and they also mention things like AVX2 and intrinsics and such.

I learn better by doing, so I would appreciate it if someone has any reference to some Rust blogs or tutorials that deal with these concepts and also include some code snippets.