DJL - TensorRT engine implementation¶
This module contains the Deep Java Library (DJL) EngineProvider for TensorRT.
It is based off the TensorRT.
We don't recommend developers use classes within this module directly. Use of these classes will couple your code to the TensorRT and make switching between engines difficult.
TensorRT is a DL library with limited support for NDArray operations. Currently, it only covers the basic NDArray creation methods. To better support the necessary preprocessing and postprocessing, you can use one of the other Engine along with it to run in a hybrid mode. For more information, see Hybrid Engine.
The latest javadocs can be found on here.
You can also build the latest javadocs locally using the following command:
# for Linux: ./gradlew javadoc
The javadocs output is generated in the
You can pull the TensorRT engine from the central Maven repository by including the following dependency:
<dependency> <groupId>ai.djl.tensorrt</groupId> <artifactId>tensorrt</artifactId> <version>0.22.1</version> <scope>runtime</scope> </dependency>
We provide a docker file to make development of tensorrt with djl easier. Follow the instructions in the docker readme to build and run the container.