NVIDIA / kvpress

LLM KV cache compression made easy

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

Commits 16 (last one 2 days ago)

Stargazers 272 (5 this week)

Watchers 6 (0 this week)

Forks 14

License apache-2.0

Ranking

RepositoryStats indexes 595,890 repositories, of these NVIDIA/kvpress is ranked #144,742 (76th percentile) for total stargazers, and #300,623 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #25,161/119,419.

NVIDIA/kvpress is also tagged with popular topics, for these it's ranked: python (#7,105/22322), pytorch (#2,060/6025), llm (#1,006/2911), large-language-models (#396/1090), transformers (#296/848), inference (#128/309)

Other Information

NVIDIA/kvpress has 1 open pull request on Github, 15 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 5 open issues and 8 closed issues.

There have been 5 releases, the latest one was published on 2024-12-12 (9 days ago) with the name v0.1.0.

All Topics

llm python pytorch kv-cache inference long-context transformers kv-cache-compression large-language-models

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

16 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 @ 02:59am, id: 884452470 / R_kgDONLesdg