FreeAIRepo
Inference & serving

NVIDIA/TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance wi

Apache-2.0Python
Stars
3.6k
Forks
872
Open issues
159
Last push
1d ago

About TransformerEngine

TransformerEngine is a free, open-source AI inference tool by NVIDIA, written mainly in Python. A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance wi. It has 3.6k GitHub stars and 872 forks, and was last updated 1d ago. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
3,589
Last update
1d ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Inference & serving tools →

TransformerEngine FAQ

Is TransformerEngine free?

Yes. TransformerEngine is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does TransformerEngine run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does TransformerEngine need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is TransformerEngine still maintained?

Yes. It was last updated 1d ago and has 159 open issues on GitHub.

What are alternatives to TransformerEngine?

Similar free, open-source tools include pytorch, keras, pytorch-lightning, DeepSpeed.

Related topics