Metadata-Version: 2.4
Name: blazeinfer
Version: 0.0.2
Summary: A high-performance, light-weight llm inference framework.
Author-email: Wenyi Xu <wenyixu101@email.com>
Project-URL: Homepage, https://github.com/xuwenyihust/BlazeInfer
Project-URL: Bug Tracker, https://github.com/xuwenyihust/BlazeInfer/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.10.0
Requires-Dist: numpy>=1.26.0
Requires-Dist: transformers>=4.40.0
Requires-Dist: accelerate>=0.32.0
Requires-Dist: tqdm
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Dynamic: license-file

<div align="center">

![# BlazeInfer](assets/logo.png)
A high-performance, light-weight llm inference framework.

</div>

<div align="center">

[![PyPI version](https://img.shields.io/pypi/v/blazeinfer.svg)](https://pypi.org/project/blazeinfer/)

</div>

--------------------------------------------------------------------------------

## About

## Features
- Optimized Attention Kernels

## Getting Started

## Acknowledgement
- [lite_llama](https://github.com/harleyszhang/lite_llama/tree/main)
