home.social

Search

5 results for “tg9541”

  1. Just a few seconds earlier the yellow foliage was brightly illuminated by the red morning sun, I swear!

    The rain was not as bad as the forecast had it.

  2. I've been testing the new llama-server 1.0.0 release: the MoE optimizations really work well for my dual RTX 3060 machine: with Gemma-4-26b-a4b I get up to 90 tokens/s for small context sizes, a 20% speed-up.

    But that's not all: MTP works very well, and I get up to 130 tokens/s (small context) and still > 90 token/s for larger ones.

  3. RE: mastodon.sdf.org/@larsbrinkhof

    The process of keeping historical systems alive tells us something about the nature of resilience:

    this is the result of a laudable personal commitment to preservation and curation in multiple fields, including the re-implementation of 1970s computer logic on hardware available today.

    Congrats!

  4. Day 317: I had meetings into the afternoon, and it got dark early. I stopped at 29984. No need to push it.

Share on Mastodon

Enter the server where you have an account.