Metadata-Version: 2.4
Name: holoscan-inference
Version: 5.0.0
Summary: The Holoscan Inference module: a meta-package for installing CUDA-specific versions
Author: NVIDIA Corporation
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/nvidia-holoscan
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.12
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Dynamic: license-file
Requires-Dist: holoscan-inference-cu13==5.0.0

# Holoscan SDK Inference module

`holoscan-inference` is a metadata-only meta-package. It installs the
CUDA-qualified Inference distribution, which provides the
`holoscan_inference` provider package and registers the
`holoscan.inference` alias.

```bash
pip install holoscan-inference
```

Installing this package pulls `holoscan-inference-cu13` and the exact matching
`holoscan-core-cu13` version. TensorRT 10 and CUDA 13 must be supplied by the
deployment environment. Installing more than one CUDA variant in the same
environment is unsupported.
