NVIDIA / TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Date Created 2023-08-16 (about a year ago)
Commits 122 (last one 4 days ago)
Stargazers 8,939 (45 this week)
Watchers 96 (0 this week)
Forks 1,031
License apache-2.0
Ranking

RepositoryStats indexes 595,890 repositories, of these NVIDIA/TensorRT-LLM is ranked #4,625 (99th percentile) for total stargazers, and #19,027 for total watchers. Github reports the primary language for this repository as C++, for repositories using this language it is ranked #247/31,840.

Other Information

NVIDIA/TensorRT-LLM has 70 open pull requests on Github, 171 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 303 open issues and 1,785 closed issues.

There have been 11 releases, the latest one was published on 2024-12-04 (17 days ago) with the name TensorRT-LLM 0.15.0 Release.

Homepage URL: https://nvidia.github.io/TensorRT-LLM

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

122 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 C++ but there's also others...

updated: 2024-12-21 @ 04:28pm, id: 679366051 / R_kgDOKH5Now