usc-isi/PipeEdge

PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices

43
/ 100
Emerging

This framework helps machine learning engineers and researchers efficiently run large neural network models like transformers on multiple, diverse edge devices. It takes your trained model and automatically splits its layers across these devices, optimizing how fast it processes data. The output is a highly performant inference system, even with limited computing resources, ideal for specialized ML deployments.

No commits in the last 6 months.

Use this if you need to run large AI models efficiently on a network of edge devices and want to maximize throughput without manual configuration.

Not ideal if you are working with small models that don't require distributed processing or if you only deploy to powerful, single-node servers.

edge-ai distributed-ml model-deployment neural-network-inference resource-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

38

Forks

28

Language

Python

License

BSD-3-Clause

Last pushed

Jan 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/usc-isi/PipeEdge"

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