[cfarm-users] cfarm109 GPU access problem

[Jacob Bachmeyer]

On 3/11/26 19:20, Zach van Rijn via cfarm-users wrote:
> [...]
>
> I reverted those changes to test one more thing; I added an
> unprivileged account to both 'video' and 'render' groups, where
> the /dev/dri* are part of group 'render'.
>
> That seems to have done the trick:
>
> zv at cfarm109:~/311$ ./llama.cpp/build-cuda/bin/llama-cli -s 0 -c
> 0 -m models/GLM-4.7-Flash-UD-Q8_K_XL.gguf
> ggml_cuda_init: found 1 CUDA devices (Total VRAM: 125771 MiB):
>    Device 0: NVIDIA Thor, compute capability 11.0, VMM: yes,
> VRAM: 125771 MiB (121255 MiB free)
>
> Loading model...
>
> [ Prompt: 54.6 t/s | Generation: 26.1 t/s ]
>
> :)
>
> Does adding all users (and new users by default) to both of
> these groups make sense, or do you think there is a better way?

Given the names of those groups and the facts that they are used for 
access control on those device nodes, I suspect that 'video' and 
'render' group membership are probably exactly the intended permissions 
to use GPGPU on that system.


-- Jacob