gptqmodel

gptqmodel

CONTAINERS IMAGES RUN BUILD

GPTQModel from https://github.com/ModelCloud/GPTQModel (installed under /opt/gptqmodel)

Inference Benchmark

Substitute the GPTQ model from HuggingFace Hub (or model path) that you want to run:

./run.sh --workdir=/opt/gptqmodel/examples/benchmark/ $(./autotag auto_gptq) \
   python3 generation_speed.py --model_name_or_path TheBloke/LLaMA-7b-GPTQ --use_safetensors --max_new_tokens=128

If you get the error Exllama kernel does not support query/key/value fusion with act-order, try adding --no_inject_fused_attention

CONTAINERS

gptqmodel:3.0.1
Aliases	gptqmodel
Requires	L4T ['>=34.1.0']
Dependencies	build-essential pip_cache:cu126 cuda:12.6 cudnn python numpy cmake onnx pytorch:2.8 torchvision huggingface_hub rust transformers
Dependants	llama-factory
Dockerfile	Dockerfile

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 gptqmodel)

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host gptqmodel:36.4.0

^{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 gptqmodel)

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

jetson-containers run $(autotag gptqmodel) 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 gptqmodel

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