MicroGPT-C in pure C hits 10M TPS on Apple M5

Check out this port of microgpt to C, posted 5 months ago. It got a 2500x speedup over the python version. https://github.com/moebiusV/cugpt

> The most atomic way to train and inference a GPT in pure, dependency-free C.

What sense of the word "atomic" is meant here?

This is not an LLM obviously , it's just for generating random names. But interesting to think of the possibilities of truly tiny language models if there were connected together.

This is pretty cool. Implemented something similar myself (a really small language model with ~10M params) just to teach myself the ML behind the LLMs. Did not implement it in C obviously, just use PyTorch, but it's interesting to go through the c file and see how he has implemented stuff I took for granted in Python in C.

Anyway, I just tested this out myself on my AMD Ryzen 9 9800x3d. I got 7647173 tok/sec using karpathy's Shakespeare dataset https://raw.githubusercontent.com/karpathy/char-rnn/master/d.... Going to play around with it and see if I can get a CUDA kernal built to see what it could do on a 5090. Claude estimates with napkin math that we could get around 2B tok/s

Honestly not sure this is impressive. I ported microgpt to zig as a learning exercise, then moved scalar engines to NEON/metal just to see what happened. Besides metal being slower (I probably did something wrong, but it could be due to the fixed costs of memory transfer into the GPU not being worth it due to the small model).

Anyways, it was also stupid fast, particularly compared to the python version. But I was pretty sure that's irrelevant to real production architectures!

It could probably go quite a bit faster using Arm SME. The entire network could fit into the ZA register.

I often wonder if there aren't some low hanging fruit in the nature of the python ecosystem surrounding AI/ML these days. I'm sure there are a lot of eyeballs looking at the problem, but every time I fire up a chat and see the python loadout, it "feels" like there might be work yet still to be done to make things as fast as possible.

And then, while I'm waiting for a response on things, the mind wanders to thinking about what the rust camp are doing, with regards to AI/ML.

To my addled mind, it really seems like the first thing to be done when getting the models firing, is turn them on their own tools and optimize, optimize, optimize. I'd sure like to know what the frontier labs are doing to squeeze those ergs out of our substrates.

Does anyone have clues what the landscape looks like outside the python tooling, vis a vis higher-performance infrastructure? Being glib about it I admit, it just seems 'odd' that the C/C++/Rust camp are letting scripting languages drive the AI/ML ship.

And the 5 years old AMD Ryzen 5 5600H is doing 7M?

Am I reading this right? Then I need to try this on Strix Halo

How much of this translates to Asahi?

Always been disappointed by the answer to that question in the past - fingers crossed this time

Model is 4K parameters - I don't know enough about that size of model to know if this impressive or not.

Imagine 10 billion tokens per second even if we make no further improvement in frontier LLMs than what we have today that would be paradigm changing.