Sasha Rush

> Last q - why don't you want to manage this yourself? Minichain is currently 2 files but I would like it to be 1 file :1st_place_medal: More though because...

The main features I need are call, embeds, streaming, and stop keywords. In theory might be nice to have caching and some of the more advanced features like Function Call...

Honestly it was mostly a learning project when I started. However, I do think it would be faster than pytorch on CPU. It contains a lot of optimizations that directly...

We could probably support Llama1, with a bit of work. Is that of interest?

This is a good change, does it impact speed? I was considering adding a rust gated feature that lets you do generic constant arithmetic, but this solution is probably better...

sorry! I'll get this checked in. just made a bunch of other changes that I need to merge in.

Would love any contribution, I'm also learning Rust and Triton on the fly. What if we try this library? It seems pretty cool. https://docs.rs/typenum/latest/typenum/

Another idea would be to explore adding testing. Not sure how unit tests work in rust, but it would be nice to have these for small sizes.

it should be. Did you have any issues?

Currently it doesn't support that model, I'll add a way to run it.