Do you host your own ML / AI / LLM? What do you use, and what do you use it for?

  • tristynalxander@mander.xyz
    link
    fedilink
    English
    arrow-up
    3
    ·
    18 hours ago

    It’s not that hard to use llama.cpp directly anyway. Why would I use a wrapper when I can just run a python script?

    • BlackLaZoR@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      5 minutes ago

      I use LMStudio, because it has quality of life improvements like nice GUI and huggingface search engine. Also they have Vulkan backend that at least on 7900XTX is ~10% faster than rocm (on LLama 3 8b Q4_0 it gets 115Tokens/s vs 105 on rocm)