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

Multi-GPU inference enabled following LLaVA repo #145

Open shouborno opened 7 months ago

shouborno commented 7 months ago

We just need the following line from the LLaVA repository to enable inference distributed on multiple devices: https://github.com/haotian-liu/LLaVA/blob/ad9fb95a5471d635e8d31c9a4a85d2e20b40ac67/llava/model/llava_arch.py#L265

Associated bug reported in this issue: https://github.com/PKU-YuanGroup/Video-LLaVA/issues/102