ctranslate2 4.7.1

Fast inference engine for Transformer models

Stars: 4310, Watchers: 4310, Forks: 443, Open Issues: 251

The OpenNMT/CTranslate2 repo was created 6 years ago and the last code push was 2 weeks ago.
The project is very popular with an impressive 4310 github stars!

How to Install ctranslate2

You can install ctranslate2 using pip

pip install ctranslate2

or add it to a project with poetry

poetry add ctranslate2

Package Details

Author

OpenNMT

License

MIT

Homepage

https://opennmt.net

PyPi:

https://pypi.org/project/ctranslate2/

Documentation:

https://opennmt.net/CTranslate2

GitHub Repo:

https://github.com/OpenNMT/CTranslate2

Classifiers

• Scientific/Engineering/Artificial Intelligence

Related Packages

Errors

A list of common ctranslate2 errors.

Code Examples

Here are some ctranslate2 code examples and snippets.

GitHub Issues

The ctranslate2 package has 251 open issues on GitHub

• Introduce AMD GPU support with ROCm HIP
• RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version
• Clang ThreadSanitizer in CI
• Integrate Clang ThreadSanitizer in tests
• GLM-4.7 support
• Qwen3-VL support (text only)
• Add a new model: WavLM
• example: semantic search using all-MiniLM-L12-v2-ct2-float32
• example: chat with qwen3-ct2-int8
• Add support for Qwen3 Embedding
• AWQ and Gemma3 compatibility problem
• Making it easier for users to get started with CTranslate2 models
• More Examples Please
• T5Gemma
• C++ API Documentation Missing / Insufficient for New Users

See more issues on GitHub