Skip to content

Latest commit

 

History

History
 
 

onnx

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 

onnx

CONTAINERS IMAGES RUN BUILD

CONTAINERS
onnx
   Builds onnx_jp46 onnx_jp51
   Requires L4T ['>=32.6']
   Dependencies build-essential python cmake numpy
   Dependants audiocraft auto_awq:0.2.4 auto_gptq:0.7.1 awq:0.1.0 bitsandbytes bitsandbytes:builder efficientvit exllama:0.0.14 exllama:0.0.15 faiss_lite flash-attention gptq-for-llama jetson-inference l4t-diffusion l4t-ml l4t-pytorch l4t-text-generation langchain langchain:samples llava local_llm minigpt4 mlc:51fb0f4 mlc:607dc5a nano_llm:24.4 nano_llm:main nanodb nanoowl nanosam nemo onnxruntime:1.11 onnxruntime:1.11-builder onnxruntime:1.16.3 onnxruntime:1.16.3-builder onnxruntime:1.17 onnxruntime:1.17-builder openai-triton openai-triton:builder optimum piper-tts pytorch:1.10 pytorch:1.9 pytorch:2.0 pytorch:2.1 pytorch:2.2 pytorch:2.3 raft sam stable-diffusion stable-diffusion-webui tam tensorrt_llm:0.10.dev0 tensorrt_llm:0.10.dev0-builder tensorrt_llm:0.5 tensorrt_llm:0.5-builder text-generation-inference text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main torch2trt torch_tensorrt torchaudio:0.10.0 torchaudio:0.9.0 torchaudio:2.0.1 torchaudio:2.1.0 torchaudio:2.2.2 torchaudio:2.3.0 torchvision:0.10.0 torchvision:0.11.1 torchvision:0.15.1 torchvision:0.16.2 torchvision:0.17.2 transformers transformers:git transformers:nvgpt tvm whisper whisperx xformers xtts
   Dockerfile Dockerfile
   Images dustynv/onnx:r32.7.1 (2023-12-11, 0.4GB)
dustynv/onnx:r35.2.1 (2023-12-12, 5.0GB)
dustynv/onnx:r35.3.1 (2023-12-11, 5.0GB)
dustynv/onnx:r35.4.1 (2023-10-07, 5.0GB)
   Notes the protobuf_apt is added as a dependency on JetPack 4 (newer versions of onnx build it in-tree)
CONTAINER IMAGES
Repository/Tag Date Arch Size
  dustynv/onnx:r32.7.1 2023-12-11 arm64 0.4GB
  dustynv/onnx:r35.2.1 2023-12-12 arm64 5.0GB
  dustynv/onnx:r35.3.1 2023-12-11 arm64 5.0GB
  dustynv/onnx:r35.4.1 2023-10-07 arm64 5.0GB

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 onnx)

# or explicitly specify one of the container images above
jetson-containers run dustynv/onnx:r35.2.1

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/onnx:r35.2.1

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 onnx)

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

jetson-containers run $(autotag onnx) 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 onnx

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