onnxruntime-ep-mlx
MLX-native ONNX Runtime execution provider for Apple Silicon. It is an out-of-tree plugin EP for ONNX Runtime 1.29 and requires no ONNX Runtime fork.
The wheel bundles MLX 0.32.2 commit 1f8e74e3 and mlx-c commit c74db530. It supports encoder, LLM
prefill, and token-at-a-time decode workloads, including quantized matmul,
attention, normalization, convolution, shape operations, and compiled
shape-specialized If, Loop, and Scan control flow.
See the complete README for operator coverage, performance results, diagnostics, build instructions, and C/C++ integration.
Install
pip install -U onnxruntime-ep-mlx
import onnxruntime as ort
import onnxruntime_ep_mlx
onnxruntime_ep_mlx.register_execution_provider_library()
session = ort.InferenceSession(
"model.onnx",
providers=["MLXExecutionProvider", "CPUExecutionProvider"],
)
outputs = session.run(None, feeds)
The package requires macOS on Apple Silicon and an ONNX Runtime 1.29 build.
1 maintainer
Metadata
1 maintainer
Release files for onnxruntime-ep-mlx 0.29.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| onnxruntime_ep_mlx-0.29.6.tar.gz | 308.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| onnxruntime_ep_mlx-0.29.6-py3-none-macosx_14_0_arm64.whl | Python 3 | none | macOS 14.0+ ARM64 | Details |
Total release size: 43.4 MB
Release files / onnxruntime_ep_mlx-0.29.6.tar.gz
| Download URL | onnxruntime_ep_mlx-0.29.6.tar.gz |
|---|---|
| Size | 308.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d0e1eea474907835936c5eec20b6489ca20dfb02de57c7b99383b64fd7ba419f
|
|
BLAKE2b-256 checksum How to use checksums |
31270b0b8b18364cf7730b8505c426dee199e762d27c8b492d43e79ed35a0e1a
|
| 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 4, 2026.
Transparency logRelease files / onnxruntime_ep_mlx-0.29.6-py3-none-macosx_14_0_arm64.whl
| Download URL | onnxruntime_ep_mlx-0.29.6-py3-none-macosx_14_0_arm64.whl |
|---|---|
| Size | 43.1 MB |
| Tags | Python 3 macOS 14.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
6ce838e9c39b799a122a6cf022c93dfb6c6f74540825acf49ece913621a7fda3
|
|
BLAKE2b-256 checksum How to use checksums |
eff26f0070bd74b6ea3cef52ecb8da2e821de044241a1f6fc6e4cb2195aa966e
|
| 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 4, 2026.
Transparency log
