search

PKU-YuanGroup / Video-LLaVA

【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
https://arxiv.org/pdf/2311.10122.pdf
Apache License 2.0
3.04k stars 220 forks source link

What is the minimum gpu ram required for the video model to run? #111

Open SarveshAtawane opened 9 months ago

SarveshAtawane commented 9 months ago

I have a PC with Quadro RTX 4000 8GB ram. The image model runs on it, but it runs out of memory for the videos. I tried different values of (pytorch_cuda_alloc_conf=max_split_size_mb) but it didn't work. Any suggetions or does it require more GPU ram. image

vidoe_error

LinB203 commented 9 months ago

Maybe 16G.