Should I struggle through constant crashes to get my 7900gre with 16gb of vram working, possibly through the headache of ONNX? Can anyone report their own success or offer advice? AMD on linux is generally lovely, SD with AMD on linux, not so much. It was much better with my RTX2080 on linux but gaming was horrible with NVIDIA drivers. I feel I could do more with the 16GB AMD card if stability wasn’t so bad. I currently have both cards running to the horror of my PSU. A1111 does NOT want to see the NVIDIA card, only the AMD. Something about the version of pytorch? More work to be done there.

  • Having a much better time back on Cinnamon default instead of Wayland. Oops!

** It heard me. Crashed again on an x/y plot but due to being away from Wayland I was able to see the terminal dump: amdgpu thermal overload! shutdown initiated! That’ll do it! Finally something easy to fix. Wonder why thermal throttling isn’t kicking in to control runaway? Will stress it once more and clock the temps this time.

Temps were exceeding 115C, phew! No idea why the default amdgpu driver has no fan control but they’re ripping like they should now. Monitoring temps has restored system stability. Using multiple amd/nvidia dedicated venv folders and careful driver choice/installation were the keys to multigpu success.

  • toothbrush@lemmy.blahaj.zone
    1·
    7 months ago

    I have run Stable Diffusion models successfully with my ancient Vega 64 with 8 gb vram. However, it does occasionally run out of memory and crash when I run models that want all 8 gigs. I have to run it without a proper DE(openbox, falkon browser with one tab only) if I dont want it to crash frequently.

    • abcdqfr@lemmy.worldOP
      0·
      7 months ago

      How bad are your crashes? Mine will either freeze the system entirely or crash the current lightdm session, sometimes recovering, sometimes freezing anyway. Needs power cycle to rescue. What is the DE you speak of? openbox?

    • abcdqfr@lemmy.worldOP
      1·
      7 months ago

      I might take the docker route for the ease of troubleshooting if nothing else. So very sick of hard system freezes/crashes while kludging through the troubleshooting process. Any words of wisdom?

  • just_another_person@lemmy.world
    0·
    7 months ago

    If you don’t understand how models use host caching, start there.

    Outside of that, you’re asking people to simplify everything into a quick answer, and there is none.

    ONNX is the “universal” standard, ensure you didn’t accidentally convert the input model into something else by accident, but more importantly, ensure when you run it and automatically convert, that the works are actually done on the GPU. ONNX defaults to CPU.

  • abcdqfr@lemmy.worldOP
    0·
    7 months ago

    Well I finally got the nvidia card working to some extent. On the recommended driver it only works in lowvram. medvram maxes vram too easily on this driver/cuda version for whatever reason. Does anyone know the current best nvidia driver for sd on linux? Perhaps 470, the other provided by the LM driver manager…?