Home Projects FasterTransformer
FasterTransformer
C++

FasterTransformer

Transformer related optimization, including BERT, GPT

by NVIDIA · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
bertgptpytorchApache-2.0C++
View on GitHub
In plain words

Optimize transformer models for better performance in AI applications.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
FasterTransformer — GitHub preview card
📈 Star history
6.44k6.43k
2026-07-042026-08-31
📈 Track FasterTransformer

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Transformer related optimization, including BERT, GPT

FasterTransformer has 6.4k stars on GitHub. It has been forked 935 times. FasterTransformer is written mainly in C++. It has been in active development since 2021. FasterTransformer is available under the Apache-2.0 license. Its main topics are bert, gpt, pytorch, transformer.

Frequently asked questions

What is FasterTransformer?

Transformer related optimization, including BERT, GPT

Is FasterTransformer open source?

FasterTransformer is an open-source project. It is released under the Apache-2.0 license.

Is FasterTransformer free?

Yes. FasterTransformer is free and open source — you can use, modify and self-host it.

What license does FasterTransformer use?

FasterTransformer is available under the Apache-2.0 license.

What language is FasterTransformer written in?

FasterTransformer is written mainly in C++.

🏅 Maintainer of this project?
olud.ai badge — FasterTransformer

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=nvidia-fastertransformer)](https://olud.ai/project/nvidia-fastertransformer.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.