uniko-cuda
NVIDIA CUDA build of uniko — the same
import uniko API as the CPU uniko package, with the ONNX Runtime CUDA
execution provider enabled for GPU-accelerated NLP/embedding inference.
Install one of uniko, uniko-cuda, or uniko-metal — they all provide
the uniko import and cannot coexist. uniko-cuda expects a CUDA-capable
NVIDIA driver on the host; the CUDA runtime libraries are resolved at load time
(not bundled), matching the standard onnxruntime-gpu model.
pip install uniko-cuda
See the main repository for documentation.
1 maintainer
Metadata
1 maintainer
Release files for uniko-cuda 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_cuda-0.3.0-cp310-abi3-manylinux_2_34_x86_64.whl | CPython 3.10 | abi3 | Linux glibc 2.34+ x86-64 | Details |
Release files / uniko_cuda-0.3.0-cp310-abi3-manylinux_2_34_x86_64.whl
| Download URL | uniko_cuda-0.3.0-cp310-abi3-manylinux_2_34_x86_64.whl |
|---|---|
| Size | 113.8 MB |
| Tags | CPython 3.10 Linux glibc 2.34+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
ea9afdfdd3620e411b27c35bb6e1555c84c1759e4343ad86b867f1864d2d75d8
|
|
BLAKE2b-256 checksum How to use checksums |
4897cee8355371f57d65403caaa7357ec638b38e7ac334c9d0d2bd9306624cde
|
| 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
