NVIDIA / TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

Date Created 2022-09-20 (2 years ago)

Commits 818 (last one a day ago)

Stargazers 1,982 (10 this week)

Watchers 34 (0 this week)

Forks 331

License apache-2.0

Ranking

RepositoryStats indexes 585,332 repositories, of these NVIDIA/TransformerEngine is ranked #25,848 (96th percentile) for total stargazers, and #63,757 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #3,958/116,570.

NVIDIA/TransformerEngine is also tagged with popular topics, for these it's ranked: python (#1,622/22032), deep-learning (#755/8403), machine-learning (#777/7939), pytorch (#470/5954), gpu (#82/903), cuda (#45/638)

Other Information

NVIDIA/TransformerEngine has 48 open pull requests on Github, 787 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 146 open issues and 206 closed issues.

There have been 14 releases, the latest one was published on 2024-11-18 (4 days ago) with the name v1.12.

Homepage URL: https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html

All Topics

fp8 gpu jax cuda python pytorch deep-learning machine-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

818 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: 2024-11-23 @ 03:42am, id: 539057023 / R_kgDOICFbfw