Skip to content

Latest commit

 

History

History
86 lines (67 loc) · 4.92 KB

README.md

File metadata and controls

86 lines (67 loc) · 4.92 KB
Raw

auto_gptq

CONTAINERS IMAGES RUN BUILD

AutoGPTQ from https://github.com/PanQiWei/AutoGPTQ (installed under /opt/AutoGPTQ)

Inference Benchmark

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

./run.sh --workdir=/opt/AutoGPTQ/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
auto_gptq:0.7.1
   Aliases auto_gptq
   Requires L4T ['>=34.1.0']
   Dependencies build-essential cuda cudnn python numpy cmake onnx pytorch:2.2 torchvision huggingface_hub rust transformers
   Dependants text-generation-webui:1.7 text-generation-webui:6a7cd01 text-generation-webui:main
   Dockerfile Dockerfile
CONTAINER IMAGES
Repository/Tag Date Arch Size
  dustynv/auto_gptq:r35.2.1 2023-12-15 arm64 6.0GB
  dustynv/auto_gptq:r35.3.1 2023-12-11 arm64 6.0GB
  dustynv/auto_gptq:r35.4.1 2023-12-14 arm64 6.0GB
  dustynv/auto_gptq:r36.2.0 2023-12-15 arm64 7.7GB

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+)

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 auto_gptq)

# or explicitly specify one of the container images above
jetson-containers run dustynv/auto_gptq:r36.2.0

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

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 auto_gptq)

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

jetson-containers run $(autotag auto_gptq) 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 auto_gptq

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