{"data":{"slug":"opennmt-ctranslate2","name":"CTranslate2","tagline":"Fast inference engine for Transformer models","github_url":"https://github.com/OpenNMT/CTranslate2","owner":"OpenNMT","repo":"CTranslate2","owner_avatar_url":"https://avatars.githubusercontent.com/u/23035727?v=4","primary_language":"C++","stars":4677,"forks":534,"topics":["avx","avx2","cpp","cuda","deep-learning","deep-neural-networks","gemm","inference","intrinsics","machine-translation","mkl","neon","neural-machine-translation","onednn","openmp","opennmt","parallel-computing","quantization","thrust","transformer-models"],"archived":false,"github_pushed_at":"2026-08-31T19:11:23+00:00","maintenance_label":"Active","stars_delta_30d":73,"url":"https://www.graphcanon.com/tools/opennmt-ctranslate2","markdown_url":"https://www.graphcanon.com/tools/opennmt-ctranslate2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opennmt-ctranslate2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opennmt-ctranslate2","description":"Fast inference engine for Transformer models","homepage_url":"https://opennmt.net/CTranslate2","license":"MIT","open_issues":286,"watchers":52,"ai_summary":"CTranslate2 is a fast inference engine for Transformer models, written in C++, supporting various hardware accelerations and optimizations.","readme_excerpt":"## Installation and usage\n\nCTranslate2 can be installed with pip:\n\n```bash\npip install ctranslate2\n```\n\nThe Python module is used to convert models and can translate or generate text with few lines of code:\n\n```python\ntranslator = ctranslate2.Translator(translation_model_path)\ntranslator.translate_batch(tokens)\n\ngenerator = ctranslate2.Generator(generation_model_path)\ngenerator.generate_batch(start_tokens)\n```\n\nSee the [documentation](https://opennmt.net/CTranslate2) for more information and examples.\n\nIf you have an AMD ROCm GPU, we provide specific Python wheels on the [releases page](https://github.com/OpenNMT/CTranslate2/releases/).","github_created_at":"2019-09-23T08:10:42+00:00","created_at":"2026-07-11T23:10:35.121179+00:00","updated_at":"2026-09-20T04:29:33.905434+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"avx","name":"avx"},{"slug":"avx2","name":"avx2"},{"slug":"cpp","name":"cpp"},{"slug":"cuda","name":"cuda"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"deep-neural-networks","name":"deep-neural-networks"},{"slug":"gemm","name":"gemm"},{"slug":"inference","name":"inference"}],"trust":{"provenance":{"is_fork":false,"github_id":210299376,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:16:45.813Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":2,"days_since_push":17,"last_release_at":"2026-08-31T19:11:59Z","stars_delta_30d":73,"open_issues_delta_30d":9},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:16:48.087Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:16:44.552Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-09-18T08:16:44.552Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:16:44.552Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["CTranslate2 can be installed via pip, and specific Python wheels are available for AMD ROCm GPUs."],"min_ram_gb":2,"requires_docker":false},"constraints":{"min_ram_gb":2,"requires_docker":false},"when_to_use":["When you need fast inference for Transformer models with support for hardware accelerations like AVX, AVX2, CUDA, and ROCm.","If your project requires C++ integration and you are looking for a lightweight, high-performance inference engine.","For applications that demand parallel computing and optimizations such as OpenMP, MKL, and OneDNN."],"when_not_to_use":["If your hardware does not support the specific accelerations CTranslate2 offers, such as AVX, AVX2, CUDA, or ROCm.","When you prefer a tool that is not written in C++ and does not require a C++ runtime environment.","If your project does not benefit from the specific optimizations like intrinsics, GEMM, or quantization that CTranslate2 provides."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:58:20.452Z"},"constraint_facets":{"min_ram_gb":2,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 2 GB RAM; CTranslate2 can be installed via pip, and specific Python wheels are available for AMD ROCm GPUs."},{"label":"Adopt for","value":"CTranslate2 is a fast inference engine for Transformer models, optimized for various hardware accelerations and written in C++."},{"label":"License detail","value":"CTranslate2 is available under the MIT license, allowing for free use and modification."}]}}