PyPI page
Home page
Author:
Casper Hansen
License:
MIT
Summary:
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
Latest version:
0.2.7.post3
Required dependencies:
accelerate
|
datasets
|
huggingface_hub
|
tokenizers
|
torch
|
transformers
|
triton
|
typing_extensions
|
zstandard
Optional dependencies:
autoawq-kernels
|
black
|
evaluate
|
flash-attn
|
griffe-typingdoc
|
intel-extension-for-pytorch
|
lm_eval
|
mkdocs-material
|
mkdocstrings-python
|
protobuf
|
scipy
|
tabulate
Downloads last day:
1,615
Downloads last week:
21,079
Downloads last month:
89,592