Skip to main content

aion-engine

Python bindings for Aion — a graph-IR tensor runtime with a Zig core, CPU and GPU. The distribution is aion-engine; the import name is aion.

Install

pip install aion-engine          # CPU
pip install aion-engine[gpu]     # + the GPU (wgpu) runtime

Prebuilt wheels for CPython 3.12/3.13 on Windows x64, Linux x86_64/aarch64 and macOS arm64/x86_64 — no Zig or C toolchain needed. The Aion runtime is static-linked into the extension module, so there is no separate aion.dll/libaion.so to ship or locate.

The GPU backend is compiled into those same wheels but links no wgpu — it dlopens wgpu-native at runtime. [gpu] adds the companion aion-wgpu wheel, which ships that library for every platform the runtime wheels target. Without it, GPU calls raise aion.AionError and CPU is unaffected.

NumPy is optional ([numpy] extra); without it use tensor.tolist() / tensor.item().

Run a model

A .aion file carries graph, weights and metadata, so this is the whole setup:

import aion, numpy as np

model = aion.load_model("model.aion")              # device="gpu" to run on GPU
out = model.run_numpy({"x": np.zeros((1, 4), "f4")})["y"]

In hot loops, bind tensors once (model.bind_input(name, t) + model.run()) instead of creating temporaries per step. KV caches and streaming state are managed by the runtime from the model's input roles — you don't thread them through Python (load_model(..., cache_capacity=, growable=) tunes it).

Build a model

Two handles, and they don't mix. aion.Tensor is data: what you write inputs into, read outputs from, and hand a layer as a weight. aion.TensorRef is a value in a graph: what ops and aion.nn layers take and return.

import aion, numpy as np
from aion import nn

ctx = aion.Context()
w = aion.tensor(np.random.randn(4, 3).astype("f4"))   # data

with aion.Builder(ctx) as b:
    x = b.input((1, 4)).rename("x")                   # TensorRef
    y = nn.Linear(w)(x).relu().rename("y")
    model = b.compile([y])

out = model.run_numpy({"x": np.ones((1, 4), "f4")})["y"]

For a reusable module, aion.compile(MyModule(), aion.spec((None, 4))) traces forward once (None = dynamic axis) and aion.export(..., "mlp.aion") writes the package. compile works on a copy of the graph, so authoring survives it: you can compile twice, and print(y) / y.numpy() evaluates just that value's cone while you keep building.

dtype takes Aion constants (aion.float32, float16, int8, int32, q8_0, q4_0) or NumPy dtypes — not strings.

GPU

ctx = aion.Context.gpu()                                  # first discrete adapter
model = aion.LoadedModel.load(ctx, "model.aion", device="gpu")

Keep feeding CPU input tensors: the model migrates them on run() and flushes outputs back for reading. A standalone tensor.to("gpu") is a move — the host copy is freed, so to("cpu") before reading it. device="gpu:1" (or adapter_index=) picks a physical adapter, power="low"/"high" picks integrated/discrete, and Context(gpus=[...]) registers several.

Examples

Runnable scripts in bindings/python/examples/, all taking --device {cpu,gpu,auto}:

silero_vad_simple.py chunked VAD, reports throughput
harrier_embed.py text embeddings, ranks documents against a query
nemotron_asr_streaming.py, nemotron_asr_mic.py streaming ASR from a wav or the mic
gemma4_e2b_generate_one.py LLM token generation

Models are produced by the converters in scripts/.

Developing from a checkout

uv sync        # environment + native build (dev group: numpy, torch, pytest, aion-wgpu)
uv run pytest

uv run rebuilds and relinks the extension when the Zig core changes — the uv cache key covers src/**/*.zig, the public headers and the build files. uv sync --reinstall-package aion-engine forces a rebuild.

Build knobs: AION_PY_OPTIMIZE (default ReleaseFast), AION_PY_CPU (native), AION_PY_TARGET, AION_PY_GPU (overrides [tool.aion] gpu in pyproject.toml). Building from source needs Zig on PATH plus a C toolchain.

Notes: prefer with for deterministic cleanup (Context.close() closes live tensors/models first); AION_DEFAULT_THREAD_COUNT sets the default context's thread count, and aion.reset_default_context() re-reads it.

Metadata

Release files for aion-engine 0.0.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for aion-engine 0.0.4
File Actions
aion_engine-0.0.4-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details for aion_engine-0.0.4-cp313-cp313-win_amd64.whl
aion_engine-0.0.4-cp313-cp313-manylinux_2_28_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64 Details for aion_engine-0.0.4-cp313-cp313-manylinux_2_28_x86_64.whl
aion_engine-0.0.4-cp313-cp313-manylinux_2_28_aarch64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ ARM64 Details for aion_engine-0.0.4-cp313-cp313-manylinux_2_28_aarch64.whl
aion_engine-0.0.4-cp313-cp313-macosx_11_0_arm64.whl CPython 3.13 CPython 3.13 macOS 11.0+ ARM64 Details for aion_engine-0.0.4-cp313-cp313-macosx_11_0_arm64.whl
aion_engine-0.0.4-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details for aion_engine-0.0.4-cp312-cp312-win_amd64.whl
aion_engine-0.0.4-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details for aion_engine-0.0.4-cp312-cp312-manylinux_2_28_x86_64.whl
aion_engine-0.0.4-cp312-cp312-manylinux_2_28_aarch64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ ARM64 Details for aion_engine-0.0.4-cp312-cp312-manylinux_2_28_aarch64.whl
aion_engine-0.0.4-cp312-cp312-macosx_11_0_arm64.whl CPython 3.12 CPython 3.12 macOS 11.0+ ARM64 Details for aion_engine-0.0.4-cp312-cp312-macosx_11_0_arm64.whl

Total release size: 26.5 MB

Release files / aion_engine-0.0.4-cp313-cp313-win_amd64.whl

Download URL aion_engine-0.0.4-cp313-cp313-win_amd64.whl
Size 1.5 MB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
87d98a0f6d749ee8c0a7052cca24f5a77a322a8ed2ee0dfdb97992e4d2d600f3
BLAKE2b-256 checksum
How to use checksums
59c21ede3e08abb84d0fda1220681a8d3a3eb22dffff27ccbcf715c56b4152aa
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp313-cp313-manylinux_2_28_x86_64.whl

Download URL aion_engine-0.0.4-cp313-cp313-manylinux_2_28_x86_64.whl
Size 5.9 MB
Tags CPython 3.13 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
a6880cae93d7ba00dadfde96d58fbeea017cc2374607b589ae40f5206056ddf6
BLAKE2b-256 checksum
How to use checksums
51a283c615eabcacd4317fda8f98657e921470884eb1479acb8599b412ef8277
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp313-cp313-manylinux_2_28_aarch64.whl

Download URL aion_engine-0.0.4-cp313-cp313-manylinux_2_28_aarch64.whl
Size 4.2 MB
Tags CPython 3.13 Linux glibc 2.28+ ARM64
SHA-256 checksum
How to use checksums
f940c3a6009196fac5f078540f3ed7bb31f9818c88c6437b43569a7036906b88
BLAKE2b-256 checksum
How to use checksums
230733c4bf00e72a160a1f1dd294098f96a5094a30516346ba7d3949417f704c
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp313-cp313-macosx_11_0_arm64.whl

Download URL aion_engine-0.0.4-cp313-cp313-macosx_11_0_arm64.whl
Size 1.7 MB
Tags CPython 3.13 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
df70826acbba6bed2d55a2c15146aff26624d6390e64050209758ade91c5aa37
BLAKE2b-256 checksum
How to use checksums
8a591397873d8740795c64035745f679472fa232532643b8b1023310872234a9
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp312-cp312-win_amd64.whl

Download URL aion_engine-0.0.4-cp312-cp312-win_amd64.whl
Size 1.5 MB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
9ba68da7d528af72206c038b1a7add4e4c34e15d0a59fe3e5728a3873271b673
BLAKE2b-256 checksum
How to use checksums
9d88492b40c32e657ce5cbea275e569fd63137e8121cc9decdab88b0aef99ba1
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp312-cp312-manylinux_2_28_x86_64.whl

Download URL aion_engine-0.0.4-cp312-cp312-manylinux_2_28_x86_64.whl
Size 5.9 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
02a0809af3d404f366c1ba6d4414b97784c7407dfccf80aba85f68e477e80bc0
BLAKE2b-256 checksum
How to use checksums
02200f48a72ad81692815af93475ea2151c46e86e0b40a67fa20b791e45b4c19
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp312-cp312-manylinux_2_28_aarch64.whl

Download URL aion_engine-0.0.4-cp312-cp312-manylinux_2_28_aarch64.whl
Size 4.2 MB
Tags CPython 3.12 Linux glibc 2.28+ ARM64
SHA-256 checksum
How to use checksums
2f06a5f1ab4685d8201ff8de11d6b0944e95f036d503f2bc376b2b3335d64fd2
BLAKE2b-256 checksum
How to use checksums
f0062f371e770eee653e071b3858a30ad0f9d8f913cf2f32153a40b29ca2c689
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 27, 2026.

Transparency log

Release files / aion_engine-0.0.4-cp312-cp312-macosx_11_0_arm64.whl

Download URL aion_engine-0.0.4-cp312-cp312-macosx_11_0_arm64.whl
Size 1.7 MB
Tags CPython 3.12 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
e739e568adf31a710ced0255653c7208cd20c4b57602eaf107f5f9dc7b25a559
BLAKE2b-256 checksum
How to use checksums
dea024ffd7d5dc7d0c597b780758d2fc67ceaa9da53b990bb2302d5510d389f8
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 27, 2026.

Transparency log

Security for aion-engine 0.0.4

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.

Full provenance

All 8 files in this release have been uploaded with provenance metadata.

Select from 8 files

Attestation for aion_engine-0.0.4-cp313-cp313-win_amd64.whl

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 27, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page