leiwang1023

Results 5 comments of leiwang1023

Me too. I use the A800 with 80G . There is a program that uses 24G and still has 57G left, which also prompts CUDA OOM

> I'm currently working with the 14B version of the VACE model. I'm using an NVIDIA L20 GPU with 48GB of VRAM. Additionally, I've used offload model and t5 cpu...

> Great job on your progress so far! However, you've encountered an issue when following the steps to modify the `model_manager` for the VACE-14B model. You mentioned that the "VACE-Wan2.1-1.3B-Preview"...

I use A800 with 80G of VRAM. If you want to run VACE-14B on a single GPU, you can set t5_cpu and offload_model=True, AND then set vae/dit-blocks/dit-vace-blocks offload to cpu...