Proof of concept - hosted webrtc #1612
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
grzegorz-roboflow
requested review from
PawelPeczek-Roboflow,
hansent,
probicheaux and
yeldarby
as code owners
hansent
reviewed
Oct 11, 2025
| request: InitialiseWebRTCPipelinePayload, | ||
| ) -> InitializeWebRTCResponse: | ||
| logger.debug("Received initialise webrtc inference pipeline request") | ||
| *_, answer = await start_worker( |
There was a problem hiding this comment.
maybe lightweight process liek this is better for STREAM API in general? like should we use this even if not streaming video to the inference server via webRTC video track...a video stream process could still be tied to webRTC connection...and if user is processing RTSP or usb device can use just data channel to manage the process / stream the results back?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Proof of concept enabling hosted webrtc in inference server
Let aiortc handle the pace
Remove all intermediate queues to reduce latency
Starting multiple webrtc connections to the same server, server is still capable of handling requests
Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
Tested locally
Any specific deployment considerations
Each webrtc connection is handled in separate process, these processes are automatically disposed when peer disconnects
Proper load balancing is desirable to evenly distribute load (RAM, GPU, etc)
Docs
N/A