sdpython/onnx-array-api

Array APIs to write ONNX Graphs

41
/ 100
Emerging

This tool helps developers translate their existing numerical functions written with NumPy into the ONNX format, which is essential for deploying machine learning models across various platforms. It takes your Python functions that use NumPy-like array operations and outputs an ONNX graph, allowing those functions to run efficiently in ONNX-compatible environments. This is specifically for developers building or optimizing conversion libraries for machine learning models.

Used by 1 other package. Available on PyPI.

Use this if you are a developer building a converter library and need to efficiently translate numerical array computations, especially those expressed with NumPy, into ONNX graphs.

Not ideal if you are an end-user simply looking to run an existing ONNX model or if you are not involved in developing conversion tools or libraries.

Machine Learning Deployment Model Conversion Deep Learning Infrastructure Numerical Computing Software Development
Maintenance 10 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Python

License

MIT

Last pushed

Jan 18, 2026

Commits (30d)

0

Dependencies

3

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sdpython/onnx-array-api"

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