uber/neuropod

A uniform interface to run deep learning models from multiple frameworks

43
/ 100
Emerging

Supports TensorFlow, PyTorch, TorchScript, Keras, and Ludwig through a standardized Problem API that decouples inference logic from framework implementation. Provides both C++ and Python bindings with zero-copy tensor operations and optional out-of-process execution, enabling runtime model swapping and multi-framework coexistence in production applications.

940 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

940

Forks

73

Language

C++

License

Apache-2.0

Last pushed

Jan 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uber/neuropod"

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