‹ BackHN Continuity

Thread

The work by Valve's Timur Kristóf on improving old AMD GPUs on Linux

472 points · 97 comments · speckx

  1. segmondy · · focus · HN ↗
    I wonder if some of these could carry over for LLM inference. It will be nice to turn more ewaste GPUs into capable processing units for LLM.
    1. marknsikora · · focus · HN ↗
      Most of these older cards are lacking the physical hardware for fp8 or other lower precisions that most quantized models use. Or the memory to run models at higher precision.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.