Package search
autoawq
- Summary: AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
- Author: Casper Hansen
- Homepage: https://github.com/casper-hansen/AutoAWQ
- Source: https://github.com/casper-hansen/AutoAWQ
- Repo profile
- Number of releases: 24
- First release: 0.0.1 on 2023-09-01T17:34:19
- Latest release: 0.2.9 on 2025-05-11T09:02:26
| Dependency | Optional |
|---|---|
| accelerate | false |
| datasets | false |
| huggingface_hub | false |
| tokenizers | false |
| torch | false |
| transformers | false |
| triton | false |
| typing_extensions | false |
| zstandard | false |
| autoawq-kernels | true |
| black | true |
| evaluate | true |
| flash-attn | true |
| griffe-typingdoc | true |
| intel-extension-for-pytorch | true |
| lm_eval | true |
| mkdocs-material | true |
| mkdocstrings-python | true |
| protobuf | true |
| scipy | true |
| tabulate | true |