.venv/transformers/docker/transformers-all-latest-gpu/Dockerfile

FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04
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='2.6.0'
# (not always a valid torch version)
ARG INTEL_TORCH_EXT='2.3.0'
# Example: `cu102`, `cu113`, etc.
ARG CUDA='cu121'

RUN apt update
RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg git-lfs
RUN git lfs install
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

# 1. Put several commands in a single `RUN` to avoid image/layer exporting issue. Could be revised in the future.
# 2. Regarding `torch` part, We might need to specify proper versions for `torchvision` and `torchaudio`.
#    Currently, let's not bother to specify their versions explicitly (so installed with their latest release versions).
RUN python3 -m pip install --no-cache-dir -U tensorflow==2.13 protobuf==3.20.3 "tensorflow_text<2.16" "tensorflow_probability<0.22" && python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime] && [ ${#PYTORCH} -gt 0 -a "$PYTORCH" != "pre" ] && VERSION='torch=='$PYTORCH'.*' ||  VERSION='torch'; echo "export VERSION='$VERSION'" >> ~/.profile && echo torch=$VERSION && [ "$PYTORCH" != "pre" ] && python3 -m pip install --no-cache-dir -U $VERSION torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/$CUDA || python3 -m pip install --no-cache-dir -U --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/$CUDA

RUN python3 -m pip uninstall -y flax jax

RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT -f https://developer.intel.com/ipex-whl-stable-cpu

RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
RUN python3 -m pip install -U "itsdangerous<2.1.0"

RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate

RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/peft@main#egg=peft

# For bettertransformer
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/optimum@main#egg=optimum

# For video model testing
RUN python3 -m pip install --no-cache-dir av==9.2.0

# Some slow tests require bnb
RUN python3 -m pip install --no-cache-dir bitsandbytes

# Some tests require quanto
RUN python3 -m pip install --no-cache-dir quanto

# `quanto` will install `ninja` which leads to many `CUDA error: an illegal memory access ...` in some model tests
# (`deformable_detr`, `rwkv`, `mra`)
RUN python3 -m pip uninstall -y ninja

# For `dinat` model
# The `XXX` part in `torchXXX` needs to match `PYTORCH` (to some extent)
RUN python3 -m pip install --no-cache-dir natten==0.15.1+torch220$CUDA -f https://shi-labs.com/natten/wheels

# For `nougat` tokenizer
RUN python3 -m pip install --no-cache-dir python-Levenshtein

# For `FastSpeech2ConformerTokenizer` tokenizer
RUN python3 -m pip install --no-cache-dir g2p-en

# For Some bitsandbytes tests
RUN python3 -m pip install --no-cache-dir einops

# 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