OpenNMT/CTranslate2

Fast inference engine for Transformer models

C++PythonCudaCMakeShellDockerfiledeep-neural-networksdeep-learningcppneonmachine-translationopenmpparallel-computingcudainferenceavxintrinsicsavx2neural-machine-translationopennmtquantizationgemmmklthrusttransformer-modelsonednn
This is stars and forks stats for /OpenNMT/CTranslate2 repository. As of 27 Apr, 2024 this repository has 1967 stars and 181 forks.

CTranslate2 CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The following model types are currently supported: Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper Decoder-only...
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
webwendy/boss-cljClojureShell0000
hahwul/xssmazeCrystalDockerfile19010
ygminds73/docker-composeDockerfilePython00260
dronecan/dronecan_dsdlcEmberScriptPythonShell40180
szpnygo/VecTextSearchGoJavaScriptMakefile2070250
securego/gosecGoHTMLShell7.1k05980
redleafnew/Chinese-STD-GB-T-7714-related-cslJavaScriptPython3.1k+26670+2
PhoebusSi/Alpaca-CoTJupyter NotebookPythonMDX2.1k02030
LC1332/CamelBell-Chinese-LoRAJupyter NotebookPython1740170
olshevski/compose-navigation-reimaginedKotlinShell4780130