cuBERT

zhihu

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

tensorflow

View on GitHub

544 Stars

85 Forks

544 Watchers

C++ Language

mit License

Cost to Build

$12.73M

Market Value

$44.05M

How is this calculated?

Growth over time

7 data points · 2021-08-01 → 2025-07-01

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about cuBERT

Question copied to clipboard

What is the zhihu/cuBERT GitHub project? Description: "Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL". Written in C++. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone cuBERT

Clone via HTTPS

git clone https://github.com/zhihu/cuBERT.git

Clone via SSH

[email protected]:zhihu/cuBERT.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the cuBERT issue tracker:

Open GitHub Issues

Similar to cuBERT

gold-miner tensorflow keras TensorFlow-Examples data-science-ipython-notebooks machine-learning-curriculum handson-ml tflearn EffectiveTensorflow TensorFlow-Tutorials TensorLayer seq2seq onnx tutorials TensorFlow-World tensorflow_cookbook tensorflow-nlp darkflow sketch-code deepo faceai gocv object_detector_app ChosunTruck lambda-packs TensorFlow-Book DeepSpeech Mask_RCNN stanford-tensorflow-tutorials facenet