Skip to content

Latest commit

 

History

History
74 lines (61 loc) · 11.3 KB

File metadata and controls

74 lines (61 loc) · 11.3 KB

numpy

CONTAINERS IMAGES RUN BUILD

CONTAINERS
numpy
   Builds numpy_jp46 numpy_jp51 numpy_jp60
   Requires L4T ['>=32.6']
   Dependencies build-essential python
   Dependants audiocraft auto_awq:0.2.4 auto_gptq:0.7.1 awq:0.1.0 bitsandbytes bitsandbytes:builder cuda-python:11.4 cudf:21.10.02 cudf:23.10.03 cuml cupy deepstream efficientvit exllama:0.0.14 exllama:0.0.15 faiss:1.7.3 faiss:1.7.3-builder faiss:1.7.4 faiss:1.7.4-builder faiss_lite faster-whisper flash-attention:2.5.6 flash-attention:2.5.6-builder flash-attention:2.5.7 flash-attention:2.5.7-builder gptq-for-llama gstreamer jetson-inference jetson-utils jupyter_clickable_image_widget jupyterlab l4t-diffusion l4t-ml l4t-pytorch l4t-tensorflow:tf1 l4t-tensorflow:tf2 langchain langchain:samples llama-index llama_cpp:0.2.57 llamaspeak llava minigpt4 mlc:0.1.0 mlc:0.1.0-builder mlc:0.1.1 mlc:0.1.1-builder nanodb nanoowl nanosam nemo numba onnx 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 openai-triton openai-triton:builder opencv:4.5.0 opencv:4.5.0-builder opencv:4.8.1 opencv:4.8.1-builder opencv:4.9.0 opencv:4.9.0-builder optimum piper-tts pycuda pytorch:1.10 pytorch:1.9 pytorch:2.0 pytorch:2.0-builder pytorch:2.1 pytorch:2.1-builder pytorch:2.2 pytorch:2.2-builder pytorch:2.3 pytorch:2.3-builder raft 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:noetic-desktop ros:noetic-ros-base ros:noetic-ros-core sam stable-diffusion 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 text-generation-inference text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main torch2trt torch_tensorrt torchaudio:0.10.0 torchaudio:0.10.0-builder torchaudio:0.9.0 torchaudio:0.9.0-builder torchaudio:2.0.1 torchaudio:2.0.1-builder torchaudio:2.1.0 torchaudio:2.1.0-builder torchaudio:2.2.2 torchaudio:2.2.2-builder torchaudio:2.3.0 torchaudio:2.3.0-builder torchvision:0.10.0 torchvision:0.11.1 torchvision:0.15.1 torchvision:0.16.2 torchvision:0.17.2 torchvision:0.18.0 transformers transformers:git transformers:nvgpt tvm voicecraft whisper whisperx wyoming-piper:master wyoming-whisper:latest xformers:0.0.26 xformers:0.0.26-builder xtts
   Dockerfile Dockerfile
   Images dustynv/numpy:r32.7.1 (2023-12-05, 0.4GB)
dustynv/numpy:r35.2.1 (2023-09-07, 5.0GB)
dustynv/numpy:r35.3.1 (2023-12-05, 5.0GB)
dustynv/numpy:r35.4.1 (2023-10-07, 5.0GB)
dustynv/numpy:r36.2.0 (2023-12-06, 0.2GB)
CONTAINER IMAGES
Repository/Tag Date Arch Size
  dustynv/numpy:r32.7.1 2023-12-05 arm64 0.4GB
  dustynv/numpy:r35.2.1 2023-09-07 arm64 5.0GB
  dustynv/numpy:r35.3.1 2023-12-05 arm64 5.0GB
  dustynv/numpy:r35.4.1 2023-10-07 arm64 5.0GB
  dustynv/numpy:r36.2.0 2023-12-06 arm64 0.2GB

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 numpy)

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

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

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

jetson-containers run $(autotag numpy) 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 numpy

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