IST-DASLab / marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Date Created 2024-01-17 (10 months ago)

Commits 14 (last one 3 months ago)

Stargazers 641 (3 this week)

Watchers 15 (0 this week)

Forks 50

License apache-2.0

Ranking

RepositoryStats indexes 589,162 repositories, of these IST-DASLab/marlin is ranked #75,247 (87th percentile) for total stargazers, and #145,936 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #12,045/117,582.

IST-DASLab/marlin is also tagged with popular topics, for these it's ranked: llm (#577/2798), kernel (#108/594)

Other Information

IST-DASLab/marlin has 4 open pull requests on Github, 4 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 25 open issues and 4 closed issues.

All Topics

llm 4bit kernel quantization

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

14 commits on the default branch (master) since jan '22

Yearly Commits

Commits to the default branch (master) per year

Issue History

Languages

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

updated: 2024-12-03 @ 11:04am, id: 744514418 / R_kgDOLGBjcg