ComfyUI : GPU and VRAM at 0%
Hi. I'm running an RTX4090 pod with the comfyui template by ai-dock to run the flux[dev] model . However, the pod shows 0% GPU usage and also 0% VRAM usage. In contrast, the RAM ahs about 30gb taken up.
The model runs slower than I expected too(although I have no point of comparison). Is this likely to be a bug in runpod's resource monitoring or is there something wrong with my pod or pod template ?
1 Reply
There is a bug in the UI, use
nvidia-smi to monitor GPU usage instead.