Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

mikeayles 3 hours ago | parent | next [-]

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?

	▲	ai_fry_ur_brain 13 minutes ago \| parent \| next [-]
		Was anyone thinking this?
	▲	ag2718 3 hours ago \| parent \| prev [-]
		You're correct that this work is not very applicable for LLMs and that the focus here is primarily on latency.

▲

RantyDave 4 hours ago | parent | prev | next [-]

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??

▲

ag2718 4 hours ago | parent [-]

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).

▲

poly2it 4 hours ago | parent [-]

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

	▲	UltraSane 3 hours ago \| parent \| next [-]
		The author actually works at Jane Street.
	▲	ag2718 4 hours ago \| parent \| prev [-]
		Yes, definitely: this type of work is applicable in domains where software run on general-purpose processors cannot meet latency or power requirements.

▲

tomrod 3 hours ago | parent | prev | next [-]

Happy to hear that KANs continue to find solid footing.

▲

Animats 4 hours ago | parent | prev | next [-]

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.

▲

throwaw12 4 hours ago | parent | next [-]

he is already at Jane Street

	▲	Animats 4 hours ago \| parent [-]
		Of course.

▲

ai_fry_ur_brain 14 minutes ago | parent | prev [-]

Sure, if they worked for 100 years maybe.. FPGA guy at jane st probably makes 600k to low seven figures... Maybe.

Not everyone in quant is a centi-millionaire, probably almost none of them in r&d actually.

▲

cwmoore an hour ago | parent | prev | next [-]

took long enough

▲

babelfish 4 hours ago | parent | prev [-]

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

▲

ag2718 4 hours ago | parent [-]

Hmm the post is still up for me?

	▲	dang 4 hours ago \| parent [-]
		For us too, but we'll put the archive link in the toptext since these things seem to vary a lot by region. p.s. Thanks for posting this and welcome to HN!