Fast inference engine for Transformer models
10K+
This repository is no longer updated. New versions are now pushed on the GitHub Container Registry.
https://github.com/OpenNMT/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.
See the installation documentation for more information about these Docker images.
Content type
Image
Digest
sha256:6054f7ee5…
Size
997.5 MB
Last updated
over 3 years ago
docker pull opennmt/ctranslate2:3.9.0-ubuntu20.04-cuda11.2