gptq-for-llama

gptq-for-llama

CONTAINERS IMAGES RUN BUILD

CONTAINERS

gptq-for-llama
Builds
Requires	L4T >=32.6
Dependencies	build-essential cuda cudnn python tensorrt numpy cmake onnx pytorch torchvision huggingface_hub rust transformers
Dependants	l4t-text-generation text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main
Dockerfile	Dockerfile
Images	dustynv/gptq-for-llama:r35.2.1 (2023-12-06, 5.9GB) dustynv/gptq-for-llama:r35.3.1 (2023-12-14, 5.9GB) dustynv/gptq-for-llama:r35.4.1 (2023-12-15, 5.9GB) dustynv/gptq-for-llama:r36.2.0 (2024-01-02, 7.6GB)
Notes	https://github.com/oobabooga/GPTQ-for-LLaMa

CONTAINER IMAGES

Repository/Tag	Date	Arch	Size
dustynv/gptq-for-llama:r35.2.1	2023-12-06	arm64	5.9GB
dustynv/gptq-for-llama:r35.3.1	2023-12-14	arm64	5.9GB
dustynv/gptq-for-llama:r35.4.1	2023-12-15	arm64	5.9GB
dustynv/gptq-for-llama:r36.2.0	2024-01-02	arm64	7.6GB

_{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 the run.sh/autotag helpers or manually put together a docker run command:

# automatically pull or build a compatible container image
./run.sh $(./autotag gptq-for-llama)

# or explicitly specify one of the container images above
./run.sh dustynv/gptq-for-llama:r36.2.0

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/gptq-for-llama:r36.2.0

^{run.sh 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:

./run.sh -v /path/on/host:/path/in/container $(./autotag gptq-for-llama)

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

./run.sh $(./autotag gptq-for-llama) my_app --abc xyz

You can pass any options to run.sh 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:

./build.sh gptq-for-llama

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