-
-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
Offload hardware acceleration to another server #11674
Comments
Similar to remote object detection, I think the latency here would be problematic. I also can't really see a situation where you would want to offload ffmpeg decoding but not offload object detection, so I don't see a practical scenario where this would be usable. |
I have multiple VMs: 1 docker, and another that transcodes other things. Since I don't need object detection on anything other than frigate, I'd leave it plugged into the docker setup. In my use case, doesn't make sense to have both a docker container and other things running on the same VM. But point taken on the potential latencies. |
Describe what you are trying to accomplish and why in non technical terms
As the topic suggested, I'd like to offload hardware acceleration to a different server that is known to have hardware acceleration enabled
Describe the solution you'd like
rffmpeg is one, there may be others.
Describe alternatives you've considered
Haven't tried any
Additional context
None at this time.
The text was updated successfully, but these errors were encountered: