ndonnx
An ONNX-backed array library that is compliant with the Array API standard.
Installation
Releases are available on PyPI and conda-forge.
# using pip
pip install ndonnx
# using conda
conda install ndonnx
# using pixi
pixi add ndonnx
Development
You can install the package in development mode using:
git clone https://github.com/quantco/ndonnx
cd ndonnx
# For Array API tests
git submodule update --init --recursive
pixi shell
pre-commit run -a
pip install --no-build-isolation --no-deps -e .
pytest tests -n auto
Quick start
ndonnx is an ONNX based python array library.
It has a couple of key features:
-
It implements the
Array APIstandard. Standard compliant code can be executed without changes across numerous backends such as like NumPy, JAX and now ndonnx.import numpy as np import ndonnx as ndx import jax.numpy as jnp def mean_drop_outliers(a, low=-5, high=5): xp = a.__array_namespace__() return xp.mean(a[(low < a) & (a < high)]) np_result = mean_drop_outliers(np.asarray([-10, 0.5, 1, 5])) jax_result = mean_drop_outliers(jnp.asarray([-10, 0.5, 1, 5])) onnx_result = mean_drop_outliers(ndx.asarray([-10, 0.5, 1, 5])) assert np_result == onnx_result.unwrap_numpy() == jax_result == 0.75
-
It supports ONNX export. This allows you persist your logic into an ONNX computation graph.
import ndonnx as ndx import onnx # Instantiate placeholder ndonnx array x = ndx.array(shape=("N",), dtype=ndx.float32) y = mean_drop_outliers(x) # Build and save ONNX model to disk model = ndx.build({"x": x}, {"y": y}) onnx.save(model, "mean_drop_outliers.onnx")
You can then make predictions using a runtime of your choice.
import onnxruntime as ort import numpy as np inference_session = ort.InferenceSession("mean_drop_outliers.onnx") prediction, = inference_session.run(None, { "x": np.array([-10, 0.5, 1, 5], dtype=np.float32), }) assert prediction == 0.75
In the future we will be enabling a stable API for an extensible data type system. This will allow users to define their own data types and operations on arrays with these data types.
Array API coverage
Array API compatibility tested against the official array-api-tests suite.
Missing coverage is tracked in the skips.txt file.
Contributions are welcome!
Run the tests with:
pixi run arrayapitests
1 maintainer
Metadata
1 maintainer
Release files for ndonnx 0.23.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ndonnx-0.23.0.tar.gz | 354.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ndonnx-0.23.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 438.2 kB
Release files / ndonnx-0.23.0.tar.gz
| Download URL | ndonnx-0.23.0.tar.gz |
|---|---|
| Size | 354.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3e7e2e0001f2a9c2a77e6ae191513d00bbc388dcca2ff13b8ed4a5cde5c302d1
|
|
BLAKE2b-256 checksum How to use checksums |
0294ee450d31b70aeeda0e1f0b4f369d17819ce8395b2bee2a3a4d456fa0505e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.
Transparency logRelease files / ndonnx-0.23.0-py3-none-any.whl
| Download URL | ndonnx-0.23.0-py3-none-any.whl |
|---|---|
| Size | 83.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c9a7d3a69e0f48498fe0e82f51b6b66a2553eb0a4776b7373b03496557d8eba4
|
|
BLAKE2b-256 checksum How to use checksums |
c9a981c5ae589ea7a4b9525e3b24a5768964188740c489fe8751262b44e004a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.
Transparency log
