6 comments

  • mikeayles 18 minutes 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?

    • ag2718 14 minutes ago
      You're correct that this work is not very applicable for LLMs and that the focus here is primarily on latency.
  • tomrod 11 minutes ago
    Happy to hear that KANs continue to find solid footing.
  • Animats 1 hour 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.
  • RantyDave 1 hour 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??
    • ag2718 1 hour 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).

      • poly2it 56 minutes ago
        I'm not in HFT, but I assume this is also an interesting applicable domain?
        • ag2718 52 minutes ago
          Yes, definitely: this type of work is applicable in domains where software run on general-purpose processors cannot meet latency or power requirements.
  • babelfish 1 hour ago
    Archive link, as it looks like the original post was taken down: https://web.archive.org/web/20260609200156/https://aarushgup...
    • ag2718 1 hour ago
      Hmm the post is still up for me?
      • dang 34 minutes ago
        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!