Metadata-Version: 2.1
Name: autoawq_kernels
Version: 0.0.2
Summary: AutoAWQ Kernels implements the AWQ kernels.
Home-page: https://github.com/casper-hansen/AutoAWQ_kernels
Author: Casper Hansen
License: MIT
Keywords: awq,autoawq,quantization,transformers
Platform: linux
Platform: windows
Classifier: Environment :: GPU :: NVIDIA CUDA :: 11.8
Classifier: Environment :: GPU :: NVIDIA CUDA :: 12
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
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 :: C++
Requires-Python: >=3.8.0
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch >=2.0.1

# AutoAWQ Kernels

AutoAWQ Kernels is a new package that is split up from the [main repository](https://github.com/casper-hansen/AutoAWQ) in order to avoid compilation times.

## Requirements

- Windows: Must use WSL2.
- GPU: Must be compute capability 7.5 or higher.
- CUDA Toolkit: Must be 11.8 or higher.

## Install

### Install from PyPi

```
pip install autoawq-kernels
```

### Build from source

```
git clone https://github.com/casper-hansen/AutoAWQ_kernels
cd AutoAWQ_kernels
pip install -e .
```
