• fartsparkles
    Aquileo | link
    Aquileo | fedilink
    English
    Aquileo | arrow-up
    12
    Aquileo | arrow-down
    1
    ·
    3 days ago

    It seems to have been a plan for a long time, given their huge shift to unified memory architectures across most of their hardware.

    They’re pretty much the only vendor where you can cost-effectively deploy a foundational LLM locally.

    • eickerOP
      Aquileo | link
      Aquileo | fedilink
      English
      Aquileo | arrow-up
      5
      ·
      3 days ago

      It would seem so. On the other hand, it is puzzling that they did not also allocate the necessary resources to the development of LLMs. 🤷

    • eleitl@lemmy.zip
      Aquileo | link
      Aquileo | fedilink
      English
      Aquileo | arrow-up
      2
      ·
      3 days ago

      Still nobody build a unified memory model with HBM. I would buy Apple hardware, then. If I can put Linux on it.

      Perhaps I can buy a used Instict with generics science acceleration, once the smoke clears. And add a couple solar kWp to my capacity.