jy-yuan / KIVI

[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Date Created 2024-02-02 (10 months ago)

Commits 54 (last one 2 months ago)

Stargazers 256 (1 this week)

Watchers 5 (0 this week)

Forks 23

License mit

Ranking

RepositoryStats indexes 595,856 repositories, of these jy-yuan/KIVI is ranked #151,483 (75th percentile) for total stargazers, and #335,688 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #26,496/119,431.

jy-yuan/KIVI is also tagged with popular topics, for these it's ranked: llm (#1,045/2913), natural-language-processing (#529/1429), large-language-models (#416/1090), transformer (#363/1018), llama (#247/547), inference (#132/309)

Other Information

jy-yuan/KIVI has Github issues enabled, there are 8 open issues and 18 closed issues.

Homepage URL: https://arxiv.org/abs/2402.02750

All Topics

llm llama inference transformer quantization large-language-models natural-language-processing

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

54 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: 2024-12-20 @ 08:00am, id: 751957145 / R_kgDOLNH0mQ