Skip to content
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

Added parallel inference support to FrameSet #161

Merged
merged 7 commits into from
Dec 11, 2023

Conversation

cat101
Copy link
Member

@cat101 cat101 commented Dec 4, 2023

Added a threadpool to allow concurrent inference requests. Parallelism, allows us to use LandingEdge pipelining ability (i.e. decode and process images while running inference on GPU). It also maximizes throughput on devices with multiple GPUs.

As part of this work I had to modify the Timer class to be able to support concurrency

@srcolinas
Copy link
Contributor

Are you adding some tests?

@cat101
Copy link
Member Author

cat101 commented Dec 4, 2023

Are you adding some tests?

Good catch. I added one to exercise the new code

landingai/pipeline/frameset.py Outdated Show resolved Hide resolved
landingai/pipeline/frameset.py Outdated Show resolved Hide resolved
landingai/pipeline/frameset.py Outdated Show resolved Hide resolved
@cat101 cat101 merged commit 010d669 into main Dec 11, 2023
7 checks passed
@cat101 cat101 deleted the matias-edgepredic-pipelineing branch December 11, 2023 17:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants