tungngreen/PipelineScheduler

PipelineScheduler optimizes workload distribution between servers and edge devices, setting optimal batch sizes to maximize throughput and minimize latency amid content dynamics and network instability. It also addresses resource contention with spatiotemporal inference scheduling to reduce co-location interference.

47
/ 100
Emerging

This system helps operations engineers and IT managers automatically manage and optimize video analytics pipelines running across servers and edge devices like cameras. It takes live video streams and inference models as input, and outputs optimized processing decisions that maximize video analysis speed and minimize delays, even when network conditions or video content changes. It's designed for those responsible for deploying and maintaining high-performance, real-time video analytics infrastructure.

Use this if you need to run complex video analytics workflows across distributed hardware, ensuring maximum speed and minimal delay while automatically adapting to real-time changes in network conditions and video content.

Not ideal if your video analytics are run on a single, isolated device without distributed processing or dynamic environmental challenges.

edge-computing video-analytics real-time-processing distributed-systems resource-optimization
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

C++

License

MIT

Category

mlops-end-to-end

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mlops/tungngreen/PipelineScheduler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.