https://github.com/dusty-nv/jetson-containers/packages/llm/llama_cpp
50K+
/opt/llama.cpp)/opt/llama-cpp-python)Warning
Starting with version 0.1.79, the model format has changed from GGML to GGUF. Existing GGML models can be converted using the `convert-llama-ggmlv3-to-gguf.py` script in [`llama.cpp`](https://github.com/ggerganov/llama.cpp) (or you can often find the GGUF conversions on [HuggingFace Hub](https://huggingface.co/models?search=GGUF))
There are two branches of this container for backwards compatability:
llama_cpp:gguf (the default, which tracks upstream master)llama_cpp:ggml (which still supports GGML model format)There are a couple patches applied to the legacy GGML fork:
__fp16 typedef in llama.h on ARM64 (use half with NVCC)You can use llama.cpp's built-in main tool to run GGUF models (from HuggingFace Hub or elsewhere)
./run.sh --workdir=/opt/llama.cpp/bin $(./autotag llama_cpp) /bin/bash -c \
'./main --model $(huggingface-downloader TheBloke/Llama-2-7B-GGUF/llama-2-7b.Q4_K_S.gguf) \
--prompt "Once upon a time," \
--n-predict 128 --ctx-size 192 --batch-size 192 \
--n-gpu-layers 999 --threads $(nproc)'
> the
--modelargument expects a .gguf filename (typically theQ4_K_Squantization is used)
> if you're trying to load Llama-2-70B, add the--gqa 8flag
To use the Python API and benchmark.py instead:
./run.sh --workdir=/opt/llama.cpp/bin $(./autotag llama_cpp) /bin/bash -c \
'python3 benchmark.py --model $(huggingface-downloader TheBloke/Llama-2-7B-GGUF/llama-2-7b.Q4_K_S.gguf) \
--prompt "Once upon a time," \
--n-predict 128 --ctx-size 192 --batch-size 192 \
--n-gpu-layers 999 --threads $(nproc)'
| Model | Quantization | Memory (MB) |
|---|---|---|
TheBloke/Llama-2-7B-GGUF | llama-2-7b.Q4_K_S.gguf | 5,268 |
TheBloke/Llama-2-13B-GGUF | llama-2-13b.Q4_K_S.gguf | 8,609 |
TheBloke/LLaMA-30b-GGUF | llama-30b.Q4_K_S.gguf | 19,045 |
TheBloke/Llama-2-70B-GGUF | llama-2-70b.Q4_K_S.gguf | 37,655 |
llama_cpp:0.2.57 | |
|---|---|
| Aliases | llama_cpp |
| Requires | L4T ['>=34.1.0'] |
| Dependencies | build-essential cuda cudnn python cmake numpy huggingface_hub |
| Dependants | langchain langchain:samples text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main |
| Dockerfile | Dockerfile |
| Repository/Tag | Date | Arch | Size |
|---|---|---|---|
dustynv/llama_cpp:ggml-r35.2.1 | 2023-12-05 | arm64 | 5.2GB |
dustynv/llama_cpp:ggml-r35.3.1 | 2023-12-06 | arm64 | 5.2GB |
dustynv/llama_cpp:ggml-r35.4.1 | 2023-12-19 | arm64 | 5.2GB |
dustynv/llama_cpp:ggml-r36.2.0 | 2023-12-19 | arm64 | 5.1GB |
dustynv/llama_cpp:gguf-r35.2.1 | 2023-12-15 | arm64 | 5.1GB |
dustynv/llama_cpp:gguf-r35.3.1 | 2023-12-19 | arm64 | 5.2GB |
dustynv/llama_cpp:gguf-r35.4.1 | 2023-12-15 | arm64 | 5.1GB |
dustynv/llama_cpp:gguf-r36.2.0 | 2023-12-19 | arm64 | 5.1GB |
dustynv/llama_cpp:r35.2.1 | 2023-08-29 | arm64 | 5.2GB |
dustynv/llama_cpp:r35.3.1 | 2023-08-15 | arm64 | 5.2GB |
dustynv/llama_cpp:r35.4.1 | 2023-08-13 | arm64 | 5.1GB |
dustynv/llama_cpp:r36.2.0 | 2024-02-22 | arm64 | 5.3GB |
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 llama_cpp)
# or explicitly specify one of the container images above
jetson-containers run dustynv/llama_cpp:r36.2.0
# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/llama_cpp: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 llama_cpp)
To launch the container running a command, as opposed to an interactive shell:
jetson-containers run $(autotag llama_cpp) 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 llama_cpp
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
sha256:178e4173a…
Size
3.3 GB
Last updated
over 1 year ago
docker pull dustynv/llama_cpp:b5283-r36.4-cu128-24.04