Ditching CUDA for AMD ROCm for more accessible LLM inference. Ryzen APUs Edition.
medium.com
We test the limits of ROCm compatibility (CUDA’s alternative) using Ryzen APUs, for GPU accelerated at-home LLM training.
  • Geoe0@alien.topBEnglish
    1·
    1 year ago

    Wow I only need to recompile everything 😂 Im a big amd fan, but scnr in this case