home.social

#5700xt — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #5700xt, aggregated by home.social.

  1. Spent months thinking my Ryzen was broken due to reboots and error logs. Turns out it was my driver.

    Needlessly increased the voltage curve incrementally for nothing. Spent multiple days debugging.

    Good to know errors can't necessarily be trusted without further investigation and analysis.

    I can now reliably trigger the errors on startup by running some broken workload on my

  2. After some trial and error, I now have AMD GPU accelerated LLMs running locally on my Ollama instance. I have an external 5700XT (gfx1010), which is not officially supported by ROCm. However, RDNA2 gfx1030 is supported.

    So if you want to have a 5700XT working you need to:
    - Install: sudo dnf rocblas
    - Go to: /usr/lib64/rocblas/library
    - Execute: sudo ln -s TensileLibrary_lazy_gfx1030.dat TensileLibrary_lazy_gfx1010.dat
    - Edit systemd Ollama.service to let it know you have a 10.1.0 (that's what the gfx1010 stands for) via an environment variable by editing the file sudo nano /etc/systemd/system/ollama.service

    It should look like this:
    [Service]
    Environment="HSA_OVERRIDE_GFX_VERSION=10.1.0"

    What is cool is that the iGPU is also loaded up and it's CU cores and VRAM are available too!

    #ollama #5700XT #amdgpu #llm #opensource