-
Notifications
You must be signed in to change notification settings - Fork 35
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Real Time Video Processing #3
Comments
Hi, |
It is truly possible to realize the code. You can refer the vllm (simple idea, just need a queue to process while kv-cache would immensely increase the inference time.) |
If a video stream contains many scene changes or camera switches, still no need to reset the model (input) state? |
if i want to support real time video streaming, how i should modify the code? @guohengkai |
Our model can process videos with scene changes without requiring any modifications. |
Thank you for answer to my quick question. |
Hello,
Does it support real time video streaming or works only with pre-recorded videos?
The text was updated successfully, but these errors were encountered: