https://github.com/dusty-nv/jetson-containers/packages/llm/nano_llm
100K+
Note
[`NanoLLM`](https://dusty-nv.github.io/NanoLLM) is a lightweight, optimized library for LLM inference and multimodal agents. For more info, see these resources: * Repo - [`github.com/dusty-nv/NanoLLM`](https://github.com/dusty-nv/NanoLLM) * Docs - [`dusty-nv.github.io/NanoLLM`](https://dusty-nv.github.io/NanoLLM) * Jetson AI Lab - [Live Llava](https://www.jetson-ai-lab.com/tutorial_live-llava.html), [NanoVLM](https://www.jetson-ai-lab.com/tutorial_nano-vlm.html), [SLM](https://www.jetson-ai-lab.com/tutorial_slm.html)
nano_llm:main | |
|---|---|
| Aliases | nano_llm |
| Requires | L4T ['>=35'] |
| Dependencies | build-essential cuda:11.4 cudnn python numpy cmake onnx pytorch:2.2 cuda-python faiss faiss_lite torchvision huggingface_hub rust transformers tensorrt torch2trt nanodb mlc riva-client:python opencv gstreamer jetson-inference torchaudio onnxruntime |
| Dockerfile | Dockerfile |
nano_llm:24.4 | |
|---|---|
| Requires | L4T ['>=35'] |
| Dependencies | build-essential cuda:11.4 cudnn python numpy cmake onnx pytorch:2.2 cuda-python faiss faiss_lite torchvision huggingface_hub rust transformers tensorrt torch2trt nanodb mlc riva-client:python opencv gstreamer jetson-inference torchaudio onnxruntime |
| Dockerfile | Dockerfile |
| Images | dustynv/nano_llm:24.4-r35.4.1 (2024-04-15, 8.5GB)dustynv/nano_llm:24.4-r36.2.0 (2024-04-15, 9.7GB) |
| Repository/Tag | Date | Arch | Size |
|---|---|---|---|
dustynv/nano_llm:24.4-r35.4.1 | 2024-04-15 | arm64 | 8.5GB |
dustynv/nano_llm:24.4-r36.2.0 | 2024-04-15 | arm64 | 9.7GB |
dustynv/nano_llm:r35.4.1 | 2024-04-15 | arm64 | 8.5GB |
dustynv/nano_llm:r36.2.0 | 2024-04-15 | arm64 | 9.7GB |
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+)
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 nano_llm)
# or explicitly specify one of the container images above
jetson-containers run dustynv/nano_llm:24.4-r36.2.0
# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/nano_llm:24.4-r36.2.0
jetson-containers run forwards arguments todocker run with some defaults added (like--runtime nvidia, mounts a/datacache, 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 nano_llm)
To launch the container running a command, as opposed to an interactive shell:
jetson-containers run $(autotag nano_llm) 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.
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 nano_llm
The dependencies from above will be built into the container, and it'll be tested during. Run it with --help for build options.
Content type
Image
Digest
sha256:ca5cfc9eb…
Size
12.7 GB
Last updated
almost 2 years ago
docker pull dustynv/nano_llm:r36.4.0