vllm-project / vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Date Created 2023-02-09 (about a year ago)

Commits 3,290 (last one 7 hours ago)

Stargazers 29,688 (91 this week)

Watchers 242 (0 this week)

Forks 4,482

License apache-2.0

Ranking

RepositoryStats indexes 579,238 repositories, of these vllm-project/vllm is ranked #696 (99th percentile) for total stargazers, and #5,320 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #123/115,001.

vllm-project/vllm is also tagged with popular topics, for these it's ranked: pytorch (#19/5908), llm (#15/2654), gpt (#15/1098), transformer (#4/992), cuda (#1/629), llama (#5/513), mlops (#3/410), inference (#4/298), llmops (#3/159)

Other Information

vllm-project/vllm has 444 open pull requests on Github, 3,208 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 1,811 open issues and 3,344 closed issues.

There have been 41 releases, the latest one was published on 2024-10-17 (20 days ago) with the name v0.6.3.post1.

Homepage URL: https://docs.vllm.ai

All Topics

amd gpt hpu llm tpu xpu cuda rocm llama mlops llmops pytorch trainium inference inferentia llm-serving transformer model-serving

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

3,290 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: 2024-11-07 @ 12:04am, id: 599547518 / R_kgDOI7xefg