1. Jetson Container 시작하기
방법 1) 깡통 컨테이너에서 시작하기 (세팅)
nvidia/l4t-base:r32.4.3
sudo docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/l4t-base:r32.4.3
https://developer.nvidia.com/embedded/learn/tutorials/jetson-container
Your First Jetson Container
What is a container? A container is an executable unit of software where an application and its run time dependencies can all be packaged together into one entity. Since everything needed by the application is packaged with the application itself, containe
developer.nvidia.com
방법 2) 추론용 컨테이너에서 시작하기 (학습)
dustynv/jetson-inference:r35.4.1
git clone --recursive --depth=1 https://github.com/dusty-nv/jetson-inference
cd jetson-inference
docker/run.sh
https://github.com/dusty-nv/jetson-inference
GitHub - dusty-nv/jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitive
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson. - dusty-nv/jetson-inference
github.com
방법 3) 모듈형 컨테이너로 시작하기 (사용)
git clone https://github.com/dusty-nv/jetson-containers
jetson-containers run dustynv/comfyui:r36.3.0 # 예시.
https://github.com/dusty-nv/jetson-containers
GitHub - dusty-nv/jetson-containers: Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T - dusty-nv/jetson-containers
github.com
| ML (Machine Learning) | PyTorch, TensorFlow, JAX, ONNX Runtime, DeepStream, HoloScan, CTranslate2, JupyterLab |
| LLM (Large Language Models) | SGLang, vLLM, MLC, AWQ, Transformers, text-generation-webui, Ollama, llama.cpp, llama-factory, exllama, AutoGPTQ, FlashAttention, DeepSpeed, bitsandbytes, xformers |
| VLM (Vision-Language Models) | llava, llama-vision, VILA, LITA, NanoLLM, ShapeLLM, Prismatic, xtuner |
| ViT (Vision Transformers) | NanoOWL, NanoSAM, Segment Anything (SAM), Track Anything (TAM), clip_trt |
| RAG (Retrieval-Augmented Generation) | llama-index, langchain, jetson-copilot, NanoDB, FAISS, RAFT |
| L4T (Linux for Tegra) | l4t-pytorch, l4t-tensorflow, l4t-ml, l4t-diffusion, l4t-text-generation |
| CUDA (NVIDIA GPU Computing) | CuPy, cuda-python, PyCUDA, Numba, OpenCV:CUDA, cuDF, cuML |
| Robotics | Cosmos, Genesis, ROS, LeRobot, OpenVLA, 3D Diffusion Policy, Crossformer, MimicGen, OpenDroneMap, ZED |
| Graphics | stable-diffusion-webui, ComfyUI, Nerfstudio, MeshLab, PixSFM, Gsplat |
| Mamba (AI Video Processing) | Mamba, MambaVision, Cobra, Dimba, VideoMambaSuite |
| Speech Processing | Whisper, whisper_trt, Piper, Riva, Audiocraft, Voicecraft, XTTS |
| Home/IoT | homeassistant-core, wyoming-whisper, wyoming-openwakeword, wyoming-piper |
'OS 운영체제 > Linux' 카테고리의 다른 글
| [NVIDIA] 젯슨 오린 네트워크 설정 방법 (1) | 2024.12.30 |
|---|---|
| [NVIDIA] 젯슨 오린 도커 세팅하기 (0) | 2024.07.01 |
| [NVIDIA] 젯슨 오린 개발보드 초기 세팅하기 (0) | 2024.06.25 |
| [NVIDIA] 도커 컨테이너 SSD로 이동하기 (0) | 2023.12.17 |
| [NVIDIA] 도커 디폴트 런타임 설정 변경 (1) | 2023.12.05 |