Natural Language Processing
Tencent/TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
🌍 Machine Translation
C++Otherupdated Jul 18, 2025
🏆 #2,525 overall#893 of 2,559 in Natural Language Processing
bytedance /ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
$ git clone https://github.com/bytedance/ByteTransformer.gitStars
480
480
This week
—
Forks
39
39
Language
C++
License
Apache-2.0
Created
Feb 17, 2023
3.7 years old
Last push
Mar 15, 2024
Categories
GitHub topics
More in Natural Language Processing
Natural Language Processing
zhihu/cuBERT
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
C++MITupdated Nov 18, 2020
Natural Language Processing
Natural Language Processing
graykode/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
Jupyter NotebookMITupdated Feb 21, 2024
Natural Language Processing
jessevig/bertviz
▲ +7 ★ this week
BertViz: Visualize Attention in Transformer Models
PythonApache-2.0updated Jan 8, 2026
Natural Language Processing
codertimo/BERT-pytorch
▲ +1 ★ this week
Google AI 2018 BERT pytorch implementation
🤖 Language Models
PythonApache-2.0updated Sep 15, 2023
Data from GitHub · snapshot Nov 13, 2026