intel / auto-round

Advanced Quantization Algorithm for LLMs/VLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

Date Created 2024-01-04 (11 months ago)

Commits 372 (last one 6 days ago)

Stargazers 284 (12 this week)

Watchers 12 (0 this week)

Forks 25

License apache-2.0

Ranking

RepositoryStats indexes 595,856 repositories, of these intel/auto-round is ranked #140,276 (76th percentile) for total stargazers, and #178,842 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #24,332/119,431.

Other Information

intel/auto-round has 5 open pull requests on Github, 282 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 13 open issues and 55 closed issues.

There have been 8 releases, the latest one was published on 2024-12-16 (6 days ago) with the name v0.4.3: bug fix release.

Homepage URL: https://arxiv.org/abs/2309.05516

All Topics

awq gptq int4 rounding quantization neural-compressor

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

372 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-12-21 @ 04:46am, id: 738776129 / R_kgDOLAjUQQ