OpenPPL/ppl.nn

A primitive library for neural network

49
/ 100
Emerging

This is a high-performance deep-learning inference engine that helps AI developers efficiently run pre-trained neural network models. It takes various ONNX formatted models, including many popular Large Language Models, and outputs highly optimized model inferences. AI developers and machine learning engineers who need to deploy and run AI models with maximum speed and efficiency will find this useful.

1,367 stars. No commits in the last 6 months.

Use this if you need to deploy and run existing ONNX-compatible AI models, especially Large Language Models, with high performance on various hardware.

Not ideal if you are looking to train new AI models or need a low-level framework for model development from scratch.

AI model deployment Large Language Models deep learning inference neural network optimization machine learning engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,367

Forks

224

Language

C++

License

Apache-2.0

Last pushed

Nov 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OpenPPL/ppl.nn"

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