mbzuai-oryx / Video-ChatGPT

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
https://mbzuai-oryx.github.io/Video-ChatGPT
Creative Commons Attribution 4.0 International
1.17k stars 102 forks source link

hardware requirement for deploying video-chatgpt locally #27

Closed Xinxinatg closed 1 year ago

Xinxinatg commented 1 year ago

Thanks for your wonderful work! I am wondering whether it would be possible to deploy it on a server with 2 A30 gpus each of which has 24 GB VRAM.

mmaaz60 commented 1 year ago

Hi @Xinxinatg,

Thank you for your interest in our work. Our model can be easily deployed on a single 24 GB GPU. It means it can be deployed on a single A30 GPU as well. Thank You.

Xinxinatg commented 1 year ago

that's great news, thank you!

On Thu, 20 Jul 2023 at 11:31, Muhammad Maaz @.***> wrote:

Hi @Xinxinatg https://github.com/Xinxinatg,

Thank you for your interest in our work. Our model can be easily deployed on a single 24 GB GPU. It means it can be deployed on a single A30 GPU as well. Thank You.

— Reply to this email directly, view it on GitHub https://github.com/mbzuai-oryx/Video-ChatGPT/issues/27#issuecomment-1642973830, or unsubscribe https://github.com/notifications/unsubscribe-auth/ARM2HOQOOYIFI5FMK4SDJBDXRCC6XANCNFSM6AAAAAA2QWFZ2A . You are receiving this because you were mentioned.Message ID: @.***>

mmaaz60 commented 1 year ago

You are most welcome!