
cuBERT
by zhihu (organization)
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL (description from the project’s GitHub page)
Repository facts
- Stars
- 546
- Forks
- 84
- Open issues and pull requests
- 8
- Primary language
- C++
- License
- MIT License (MIT)
- Owner
- zhihu · Organization
- Created
- Mar 13, 2019
- Last push
- Nov 18, 2020
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,708: OpenNMT/CTranslate2
Fast inference engine for Transformer models
4,713 starsC++MITLast push Oct 18, 2026
Rank 9,107: underneathall/pinferencia
Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
541 starsPythonApache-2.0Last push Feb 14, 2023
Rank 8,969: Tencent/Forward
A library for high performance deep learning inference on NVIDIA GPUs.
556 starsC++Other licenseLast push Jan 29, 2022
Rank 4,492: Tencent/TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
1,550 starsC++Other licenseLast push Jul 18, 2025
Rank 43: vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
94,068 starsPythonApache-2.0Last push Oct 18, 2026
Rank 185: sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
37,276 starsPythonApache-2.0Last push Oct 18, 2026