Nvidia Nemotron 3.5 lightning and NeMo Switchyard

(blogs.nvidia.com)

35 points | by droidjj 32 minutes ago

3 comments

  • XCSme 5 minutes ago
    The new Meta 30B models seems A LOT better:

    https://aibenchy.com/compare/meta-muse-glimmer-30b-xhigh/nvi...

    • eli 0 minutes ago
      The top 4 models on that site are all variants of Gemini Flash? That does not match my experience at all.
    • Tactical45 1 minute ago
      At what cost difference?
  • thehamkercat 18 minutes ago
    > NeMo Switchyard, an open source library for smart routing

    > When deployed, NeMo Switchyard can intelligently direct each request to the most capable and suitable model for the job

    How do routers like this handle prompt caching when you send the second request?

    Sticky models per session? but then the second message of that session won't be sent to a suitable model, and will only be sent to the same model as previous one.

    • eli 3 minutes ago
      I've seen ones that are configurable to pick a trade off point between lower cost (cache stickiness) and routing performance (best model for that turn).

      But yeah I'm skeptical all this overhead is worth it.

    • embedding-shape 14 minutes ago
      The repo is probably a better entrypoint to it, bit more concise description than the press releases: https://github.com/NVIDIA-NeMo/Switchyard (Notably: "Experimental software. Not for production use."). Unclear if they actually want you to deploy it or not, press release says yes, README says no, do with that what you will.

      Doesn't seem to mention "cache" in the README nor the docs, but the code has mentions of it (https://github.com/search?q=repo%3ANVIDIA-NeMo%2FSwitchyard+...), I'm not sure what their thinking is there. "Good luck" essentially? Seems to be per-provider at best, but weird position for a routing library to take.

      • thehamkercat 10 minutes ago
        I personally think it's snake-oil marketing with all these smart-model-routing products/projects

        prompt-cache won't work with these

        • try-working 6 minutes ago
          caching works perfectly fine with routers.
  • WalterGR 11 minutes ago
    24 comments so far about Nemotron: https://news.ycombinator.com/item?id=49257947