llama.cpp uses CPU llvmpipe, not AMD GPU, on Fedora
After Fedora Mesa and kernel updates, llama.cpp sees only the llvmpipe CPU Vulkan device and not the AMD GPU.
Tier II · Emerging Problems that are still building up.
8 public reports · first reported 9 October 2026 · last reported 9 October 2026
What's going wrong
After recent Fedora kernel and Mesa updates, llama.cpp stops using an AMD graphics card and falls back to llvmpipe, a software Vulkan device that runs on the CPU.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 8 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.