jp6/cu122/: autoawq-kernels-0.0.6+cu122 metadata and description

AutoAWQ Kernels implements the AWQ kernels.

author	Casper Hansen
classifiers	Environment :: GPU :: NVIDIA CUDA :: 11.8 Environment :: GPU :: NVIDIA CUDA :: 12 License :: OSI Approved :: MIT License Natural Language :: English Programming Language :: Python :: 3.8 Programming Language :: Python :: 3.9 Programming Language :: Python :: 3.10 Programming Language :: Python :: 3.11 Programming Language :: C++
description_content_type	text/markdown
keywords	awq,autoawq,quantization,transformers
license	MIT
platform	linux windows
requires_dist	torch >=2.0.1
requires_python	>=3.8.0

Because this project isn't in the mirror_whitelist, no releases from root/pypi are included.

File	Tox results	History
autoawq_kernels-0.0.6+cu122-cp310-cp310-linux_aarch64.whl Size 17 MB Type Python Wheel Python 3.10		Uploaded to jp6/cu122 by jp6 2024-03-30 16:46:02

AutoAWQ Kernels

AutoAWQ Kernels is a new package that is split up from the main repository in order to avoid compilation times.

Windows: Must use WSL2.
NVIDIA:
- GPU: Must be compute capability 7.5 or higher.
- CUDA Toolkit: Must be 11.8 or higher.
AMD:
- ROCm: Must be 5.6 or higher.

The package is available on PyPi with CUDA 12.1.1 wheels:

pip install autoawq-kernels

For ROCm and other CUDA versions, you can use the wheels published at each release:

pip install https://github.com/casper-hansen/AutoAWQ_kernels/releases/download/v0.0.2/autoawq_kernels-0.0.2+rocm561-cp310-cp310-linux_x86_64.whl

You can also build from source:

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

To build for ROCm, you need to first install the following packages rocsparse-dev hipsparse-dev rocthrust-dev rocblas-dev hipblas-dev.