Metadata-Version: 2.1
Name: optimum-pipelines
Version: 0.0.1
Summary: An inference pipelines framework for optimum.
Author: David Corvoysier
Maintainer-email: "HuggingFace Inc. Special Ops Team" <hardware@huggingface.co>
License: Apache-2.0
Project-URL: homepage, https://github.com/huggingface/optimum-pipelines
Keywords: inference,machine-learning
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9.0
Description-Content-Type: text/markdown
Requires-Dist: pydantic >=2.9.1
Provides-Extra: dev
Requires-Dist: build ; extra == 'dev'
Requires-Dist: pytest ; extra == 'dev'
Requires-Dist: ruff ; extra == 'dev'
Requires-Dist: datamodel-code-generator ; extra == 'dev'
Requires-Dist: jinja2 ; extra == 'dev'

# Optimum Pipelines

🤗 `optimum-pipelines` is a framework for maintaining and contributing inference pipelines for [Hugging Face hub models](https://huggingface.co/models).

The pipelines are objects implementing workflows corresponding to several tasks applied to hub models.

They provide a unified API for local or remote inference, with a dedicated [JSON schema](https://github.com/huggingface/huggingface.js/tree/main/packages/tasks/src/tasks) for each task.

## Building the package

```shell
$ make package
```

## Running the tests

First, install the package:

```shell
$ python -m pip install dist/optimum_pipelines-<version>.tar.gz
```

```shell
$ make test
```
