mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-29 01:02:25 +06:00
4fc708f98c
* added exllama kernels support for awq models * doc * style * Update src/transformers/modeling_utils.py Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> * refactor * moved exllama post init to after device dispatching * bump autoawq version * added exllama test * style * configurable exllama kernels * copy exllama_config from gptq * moved exllama version check to post init * moved to quantization dockerfile --------- Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
50 lines
2.3 KiB
Docker
50 lines
2.3 KiB
Docker
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
|
|
LABEL maintainer="Hugging Face"
|
|
|
|
ARG DEBIAN_FRONTEND=noninteractive
|
|
|
|
# Use login shell to read variables from `~/.profile` (to pass dynamic created variables between RUN commands)
|
|
SHELL ["sh", "-lc"]
|
|
|
|
# The following `ARG` are mainly used to specify the versions explicitly & directly in this docker file, and not meant
|
|
# to be used as arguments for docker build (so far).
|
|
|
|
ARG PYTORCH='2.2.0'
|
|
# Example: `cu102`, `cu113`, etc.
|
|
ARG CUDA='cu118'
|
|
|
|
RUN apt update
|
|
RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python python3-pip ffmpeg
|
|
RUN python3 -m pip install --no-cache-dir --upgrade pip
|
|
|
|
ARG REF=main
|
|
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
|
|
|
RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' || VERSION='torch'; echo "export VERSION='$VERSION'" >> ~/.profile
|
|
RUN echo torch=$VERSION
|
|
# `torchvision` and `torchaudio` should be installed along with `torch`, especially for nightly build.
|
|
# Currently, let's just use their latest releases (when `torch` is installed with a release version)
|
|
RUN python3 -m pip install --no-cache-dir -U $VERSION torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/$CUDA
|
|
|
|
RUN python3 -m pip install --no-cache-dir -e ./transformers[dev-torch]
|
|
|
|
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
|
|
|
|
# Add bitsandbytes for mixed int8 testing
|
|
RUN python3 -m pip install --no-cache-dir bitsandbytes
|
|
|
|
# Add auto-gptq for gtpq quantization testing
|
|
RUN python3 -m pip install --no-cache-dir auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
|
|
|
|
# Add optimum for gptq quantization testing
|
|
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/optimum@main#egg=optimum
|
|
|
|
# Add aqlm for quantization testing
|
|
RUN python3 -m pip install --no-cache-dir aqlm[gpu]==1.0.2
|
|
|
|
# Add autoawq for quantization testing
|
|
RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp38-cp38-linux_x86_64.whl
|
|
|
|
# When installing in editable mode, `transformers` is not recognized as a package.
|
|
# this line must be added in order for python to be aware of transformers.
|
|
RUN cd transformers && python3 setup.py develop |