Customize Triton Container#

Two Docker images are available from NVIDIA GPU Cloud (NGC) that make it possible to easily construct customized versions of Triton. By customizing Triton you can significantly reduce the size of the Triton image by removing functionality that you don’t require.

Currently the customization is limited as described below but future releases will increase the amount of customization that is available. It is also possible to build Triton from source to get more exact customization.

Use the script#

The script can be found in the server repository. Simply clone the repository and run to create a custom container. Note: Created container version will depend on the branch that was cloned. For example branch r24.06 should be used to create a image based on the NGC 24.06 Triton release. provides --backend, --repoagent options that allow you to specify which backends and repository agents to include in the custom image. For example, the following creates a new docker image that contains only the Pytorch and Tensorflow backends and the checksum repository agent.


python3 --backend pytorch --backend tensorflow --repoagent checksum

will provide a container tritonserver locally. You can access the container with

$ docker run -it tritonserver:latest

Note: If is run on release versions r21.08 and earlier, the resulting container will have DCGM version 2.2.3 installed. This may result in different GPU statistic reporting behavior.

Compose a specific version of Triton# requires two containers: a min container which is the base the compose container is built from and a full container from which the script will extract components. The version of the min and full container is determined by the branch of Triton is on. For example, running

python3 --backend pytorch --repoagent checksum

on branch r24.06 pulls:

  • min container

  • full container

Alternatively, users can specify the version of Triton container to pull from any branch by either:

  1. Adding flag --container-version <container version> to branch

python3 --backend pytorch --repoagent checksum --container-version 24.06
  1. Specifying --image min,<min container image name> --image full,<full container image name>. The user is responsible for specifying compatible min and full containers.

python3 --backend pytorch --repoagent checksum --image min, --image full,

Method 1 and 2 will result in the same composed container. Furthermore, --image flag overrides the --container-version flag when both are specified.


  1. All contents in /opt/tritonserver repository of the min image will be removed to ensure dependencies of the composed image are added properly.

  2. vLLM and TensorRT-LLM backends are currently not supported backends for If you want to build additional backends on top of these backends, it would be better to build it yourself by using or as a min container.

CPU-only container composition#

CPU-only containers are not yet available for customization. Please see build documentation for instructions to build a full CPU-only container. When including TensorFlow or PyTorch backends in the composed container, an additional gpu-min container is needed since this container provided the CUDA stubs and runtime dependencies which are not provided in the CPU only min container.

Build it yourself#

If you would like to do what is doing under the hood yourself, you can run with the --dry-run option and then modify the Dockerfile.compose file to satisfy your needs.

Triton with Unsupported and Custom Backends#

You can create and build your own Triton backend. The result of that build should be a directory containing your backend shared library and any additional files required by the backend. Assuming your backend is called “mybackend” and that the directory is “./mybackend”, adding the following to the Dockerfile created will create a Triton image that contains all the supported Triton backends plus your custom backend.

COPY ./mybackend /opt/tritonserver/backends/mybackend

You also need to install any additional dependencies required by your backend as part of the Dockerfile. Then use Docker to create the image.

$ docker build -t tritonserver_custom -f Dockerfile.compose .