uniko-metal
Apple Silicon (Metal / CoreML) build of
uniko — the same import uniko API as the
CPU uniko package, with the ONNX Runtime CoreML execution provider enabled for
GPU/ANE-accelerated NLP/embedding inference on macOS arm64.
Install one of uniko, uniko-cuda, or uniko-metal — they all provide
the uniko import and cannot coexist. uniko-metal is macOS/Apple-Silicon
only; the CoreML provider is statically linked (nothing extra to install).
pip install uniko-metal
See the main repository for documentation.
1 maintainer
Metadata
1 maintainer
Release files for uniko-metal 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| uniko_metal-0.3.0-cp310-abi3-macosx_11_0_arm64.whl | CPython 3.10 | abi3 | macOS 11.0+ ARM64 | Details |
Release files / uniko_metal-0.3.0-cp310-abi3-macosx_11_0_arm64.whl
| Download URL | uniko_metal-0.3.0-cp310-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 89.6 MB |
| Tags | CPython 3.10 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
fb9a4ee9157c8c13b77cef2762ac272a1a03375f55c4217faf5a660cadf42c85
|
|
BLAKE2b-256 checksum How to use checksums |
2c5b51e809291a583d5e68db3a5321cde34561f12022b13cc8d37a2ca49514bb
|
| 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 26, 2026.
Transparency log
