LLMs under Linux (LM Studio) not using GPU?

[Lars_Urban]

Hi would say, give amdgpu_top a try.
As a side node how my setup is till today:

Llama.cpp/vLLM Toolboxes for LLM inference on Strix Halo

Thank you very much @kyuz0 ! I miss something to fully see the whole resources. Setup is done with: sudo grubby --update-kernel=ALL --args=‘amd_iommu=off amdgpu.gttsize=131072 ttm.pages_limit=33554432 i also just reserved 512mb dedicated vram in bios. but executing: llama-cli --list-devices shows only 86GB: maintenance@fedora:~$ toolbox enter llama-vulkan-radv ⬢ [maintenance@toolbx ~]$ llama-cli --list-devices ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Radeon 8060S Graphics…