aurarouter-cuda12
AuraRouter Stable GPU Backend (CUDA 12.4)
This package is a "sidecar" for AuraRouter. It contains the pre-compiled binary payload required to run local LLMs on older NVIDIA GPUs or systems with legacy drivers.
What's inside?
llama-server.exe: Compiled with CUDA 12.4 support.ggml-cuda.dll: Optimized kernels for NVIDIA architectures.cudart64_12.dll&cublas64_12.dll: Required NVIDIA runtime libraries.
Requirements
- Hardware: NVIDIA GPU.
- Drivers: NVIDIA Driver version 525.60 or higher.
- AuraRouter: Must be installed in the same environment.
Usage
Simply install this package into the same virtual environment as aurarouter:
pip install aurarouter-cuda12
AuraRouter's BinaryManager will automatically detect this package and use it for local inference. It is prioritized over CPU-based backends but lower than aurarouter-cuda13.
1 maintainer
Metadata
1 maintainer
Release files for aurarouter-cuda12 0.5.8189
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| aurarouter_cuda12-0.5.8189.tar.gz | 4.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aurarouter_cuda12-0.5.8189-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.1 kB
Release files / aurarouter_cuda12-0.5.8189.tar.gz
| Download URL | aurarouter_cuda12-0.5.8189.tar.gz |
|---|---|
| Size | 4.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f7ea47c7c5edbe4ceeaad25673b5848ad5c1c121cc04966cbf97c0deffc2ac62
|
|
BLAKE2b-256 checksum How to use checksums |
5cdf1a4d7aa9faff81a80ae9520c2c8023f3ff85252b1dcf84d40cda49979028
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Mar 24, 2026.
Transparency logRelease files / aurarouter_cuda12-0.5.8189-py3-none-any.whl
| Download URL | aurarouter_cuda12-0.5.8189-py3-none-any.whl |
|---|---|
| Size | 5.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b42c7f7932b09ba81047b30e31ca795714a743f36a5b1ecaa0126bde87ed9c36
|
|
BLAKE2b-256 checksum How to use checksums |
8b8a70687b4ff4ef34f54466889164272576a3778903f2b5472caebaa22266d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Mar 24, 2026.
Transparency log
