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. A full list of features and supported models is included in the project’s repository. To start, please check out the official quickstart guide.

​

Installation and Setup

pip install ctranslate2

​

LLMs

from langchain_community.llms import CTranslate2