Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

Posted by ag2718 4 hours ago

https://web.archive.org/web/20260609200156/https://aarushgup...

Comments

Comment by mikeayles 3 hours ago

So for people wondering if it can be used to accelerate LLM inference, sadly not.

I've been trying to hit 100,000tokens/s with a 3.28m dumb model, and even this is an order of magnitude too large to benefit.

It appears to be focussed more on latency, than throughput. Happy to be corrected?

Comment by ag2718 2 hours ago

You're correct that this work is not very applicable for LLMs and that the focus here is primarily on latency.

Comment by RantyDave 4 hours ago

Right. But ... this would limit you to either extremely small models or extremely large FPGA's, yes? If there's a simple machine learning task that requires a sub microsecond latency I can see the point but otherwise??

Comment by ag2718 3 hours ago

Yes, this work is focused on accelerating very small models, typically for real-time systems that require extremely low power or low latency.

One primary application of this work is in high-energy physics (https://home.cern/smarter-decisions-at-the-speed-of-collisio...). Ultrafast and real-time learning is also very applicable for problems in quantum computing, plasma control, etc. (https://arxiv.org/pdf/2602.02005).

Comment by poly2it 3 hours ago

I'm not in HFT, but I assume this is also an interesting applicable domain?

Comment by UltraSane 2 hours ago

The author actually works at Jane Street.

Comment by ag2718 3 hours ago

Yes, definitely: this type of work is applicable in domains where software run on general-purpose processors cannot meet latency or power requirements.

Comment by 3 hours ago

Comment by tomrod 2 hours ago

Happy to hear that KANs continue to find solid footing.

Comment by Animats 3 hours ago

This guy will be hired by a high-frequency trading firm, and the next time we hear about him, he will have a net worth in 9 figures.

Comment by throwaw12 3 hours ago

he is already at Jane Street

Comment by Animats 3 hours ago

Of course.

Comment by 4 hours ago

Comment by cwmoore 1 hour ago

took long enough

Comment by babelfish 3 hours ago

Archive link, as it looks like the original post was taken down: https://web.archive.org/web/20260609200156/https://aarushgup...

Comment by ag2718 3 hours ago

Hmm the post is still up for me?

Comment by dang 3 hours ago

For us too, but we'll put the archive link in the toptext since these things seem to vary a lot by region.