Metadata-Version: 2.1
Name: vllm-client
Version: 0.2.1
Summary: Client for the vLLM API with minimal dependencies
Home-page: https://github.com/viktor-ferenczi/vllm-client
Author: Viktor Ferenczi
License: Apache 2.0
Project-URL: Homepage, https://github.com/viktor-ferenczi/vllm-client
Project-URL: Documentation, https://github.com/viktor-ferenczi/vllm-client
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aiohttp

# vLLM Client

## Overview

Client for the [vLLM](https://github.com/vllm-project/vllm) API with minimal dependencies.

## Installation

```sh
pip install vllm-client
```

## Examples

See [example.py](example.py) for the following:
- Single generation
- Streaming
- Batch inference

It should work out of the box with a vLLM API server. 

## Notes

- `sampling_params.py` needs to be kept in sync with vLLM.
  It is a simplified version of their class, containing
  only the code required on client side.

## Another programming languages

- C# [VllmClient NuGet package](https://www.nuget.org/packages/VllmClient/0.2.1)


