Skip to content

Latest commit

 

History

History
82 lines (67 loc) · 6.89 KB

README.md

File metadata and controls

82 lines (67 loc) · 6.89 KB

tensorrt

CONTAINERS IMAGES RUN BUILD

CONTAINERS
tensorrt:8.6
   Builds tensorrt-86_jp60
   Requires L4T ['==r36.*', '==cu122']
   Dependencies build-essential cuda:12.2 cudnn:8.9 python
   Dockerfile Dockerfile.deb
   Images dustynv/tensorrt:8.6-r36.2.0 (2023-12-05, 6.7GB)
tensorrt:10.0
   Requires L4T ['==r36.*', '==cu124']
   Dependencies build-essential cuda:12.4 cudnn:9.0 python
   Dockerfile Dockerfile.tar
tensorrt
   Requires L4T ['<36']
   Dependencies build-essential cuda cudnn python
   Dependants deepstream efficientvit jetson-inference jetson-utils l4t-diffusion l4t-ml l4t-pytorch l4t-tensorflow:tf1 l4t-tensorflow:tf2 nanodb nanoowl nanosam onnxruntime:1.11 onnxruntime:1.11-builder onnxruntime:1.16.3 onnxruntime:1.16.3-builder onnxruntime:1.17 onnxruntime:1.17-builder onnxruntime:1.19 onnxruntime:1.19-builder optimum piper-tts ros:foxy-desktop ros:foxy-ros-base ros:foxy-ros-core ros:galactic-desktop ros:galactic-ros-base ros:galactic-ros-core ros:humble-desktop ros:humble-ros-base ros:humble-ros-core ros:iron-desktop ros:iron-ros-base ros:iron-ros-core ros:melodic-desktop ros:melodic-ros-base ros:melodic-ros-core ros:noetic-desktop ros:noetic-ros-base ros:noetic-ros-core sam stable-diffusion-webui tam tensorflow tensorflow2 tensorrt_llm:0.10.dev0 tensorrt_llm:0.10.dev0-builder tensorrt_llm:0.5 tensorrt_llm:0.5-builder torch2trt torch_tensorrt tritonserver wyoming-piper:master xtts zed
   Images dustynv/tensorrt:8.6-r36.2.0 (2023-12-05, 6.7GB)
CONTAINER IMAGES
Repository/Tag Date Arch Size
  dustynv/tensorrt:8.6-r36.2.0 2023-12-05 arm64 6.7GB

Container images are compatible with other minor versions of JetPack/L4T:
    • L4T R32.7 containers can run on other versions of L4T R32.7 (JetPack 4.6+)
    • L4T R35.x containers can run on other versions of L4T R35.x (JetPack 5.1+)

RUN CONTAINER

To start the container, you can use jetson-containers run and autotag, or manually put together a docker run command:

# automatically pull or build a compatible container image
jetson-containers run $(autotag tensorrt)

# or explicitly specify one of the container images above
jetson-containers run dustynv/tensorrt:8.6-r36.2.0

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/tensorrt:8.6-r36.2.0

jetson-containers run forwards arguments to docker run with some defaults added (like --runtime nvidia, mounts a /data cache, and detects devices)
autotag finds a container image that's compatible with your version of JetPack/L4T - either locally, pulled from a registry, or by building it.

To mount your own directories into the container, use the -v or --volume flags:

jetson-containers run -v /path/on/host:/path/in/container $(autotag tensorrt)

To launch the container running a command, as opposed to an interactive shell:

jetson-containers run $(autotag tensorrt) my_app --abc xyz

You can pass any options to it that you would to docker run, and it'll print out the full command that it constructs before executing it.

BUILD CONTAINER

If you use autotag as shown above, it'll ask to build the container for you if needed. To manually build it, first do the system setup, then run:

jetson-containers build tensorrt

The dependencies from above will be built into the container, and it'll be tested during. Run it with --help for build options.