The efficient frontier of LLM inference

(baseten.co)

26 points | by philipkiely 1 hour ago

4 comments

  • datadrivenangel 10 minutes ago
    The author does not deeply mention that quality/intelligence is a third dimension here in addition to throughput and latency, and the frontier is jagged so quality and intelligence require bespoke benchmarks to evaluate tradeoffs for speed and cost.
  • calclavia 3 minutes ago
    good recap on the recent inference techniques!
  • brrrrrm 44 minutes ago
    this is a nice and concise writeup. what's striking to me is that these techniques really have not changed in /years/. sure, precision has become slightly lower, spec decoding acceptance has gotten slightly better and the complexity of parallelism is trickier with mixture of experts. but no new concepts in a very long time!

    the absolute most impactful improvements for inference comes at architecture design time. I firmly believe everyone who cares about impacting model efficiency should look there

    • philipkiely 31 minutes ago
      I think the biggest net new recent technique is P/D disaggregation. And that spec dec is very different now especially post DSpark/DFlash.

      But overall yes the fundamentals of LLM performance optimization have been remarkably stable over the last few years.

  • nedo_var 26 minutes ago
    [dead]