mit-han-lab / nunchaku

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Date Created 2024-11-06 (about a month ago)

Commits 45 (last one 21 days ago)

Stargazers 551 (11 this week)

Watchers 12 (0 this week)

Forks 28

License apache-2.0

Ranking

RepositoryStats indexes 598,732 repositories, of these mit-han-lab/nunchaku is ranked #85,331 (86th percentile) for total stargazers, and #179,210 for total watchers. Github reports the primary language for this repository as Cuda, for repositories using this language it is ranked #47/358.

mit-han-lab/nunchaku is also tagged with popular topics, for these it's ranked: diffusion-models (#101/646), lora (#58/279)

Other Information

mit-han-lab/nunchaku has 2 open pull requests on Github, 0 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 36 open issues and 31 closed issues.

There have been 2 releases, the latest one was published on 2024-12-08 (22 days ago) with the name Nunchaku v0.0.1 Release.

Homepage URL: https://hanlab.mit.edu/projects/svdquant

All Topics

flux lora genai mlsys quantization diffusion-models

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

45 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 Cuda but there's also others...

updated: 2024-12-29 @ 05:50pm, id: 884123664 / R_kgDONLKoEA