mirror of
https://github.com/allenai/olmocr.git
synced 2025-10-31 01:55:06 +00:00
52 lines
1.8 KiB
Plaintext
52 lines
1.8 KiB
Plaintext
FROM --platform=linux/amd64 nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu20.04
|
|
|
|
RUN apt-get update -y && apt-get install -y software-properties-common \
|
|
&& add-apt-repository ppa:deadsnakes/ppa \
|
|
&& apt-get -y update
|
|
|
|
# Install requirements specific to pdfs
|
|
RUN apt-get update && apt-get -y install python3-apt
|
|
RUN echo "ttf-mscorefonts-installer msttcorefonts/accepted-mscorefonts-eula select true" | debconf-set-selections
|
|
RUN apt-get update -y && apt-get install -y poppler-utils ttf-mscorefonts-installer msttcorefonts fonts-crosextra-caladea fonts-crosextra-carlito gsfonts lcdf-typetools
|
|
|
|
RUN apt-get update -y && apt-get install -y --no-install-recommends \
|
|
git \
|
|
python3.11 \
|
|
python3.11-dev \
|
|
python3.11-distutils \
|
|
ca-certificates \
|
|
build-essential \
|
|
curl \
|
|
unzip
|
|
|
|
RUN rm -rf /var/lib/apt/lists/* \
|
|
&& unlink /usr/bin/python3 \
|
|
&& ln -s /usr/bin/python3.11 /usr/bin/python3 \
|
|
&& ln -s /usr/bin/python3 /usr/bin/python \
|
|
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python \
|
|
&& pip3 install -U pip
|
|
|
|
RUN apt-get update && apt-get -y install python3.11-venv
|
|
ADD --chmod=755 https://astral.sh/uv/install.sh /install.sh
|
|
RUN /install.sh && rm /install.sh
|
|
|
|
# Flash inference install sooner
|
|
RUN /root/.local/bin/uv pip install --system flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
|
|
|
|
ENV PYTHONUNBUFFERED=1
|
|
WORKDIR /root
|
|
COPY pyproject.toml pyproject.toml
|
|
COPY pdelfin/version.py pdelfin/version.py
|
|
|
|
RUN /root/.local/bin/uv pip install --system --no-cache -e .[inference]
|
|
|
|
COPY pdelfin pdelfin
|
|
|
|
# TODO You can remove this once pypdf > 5.10 comes out
|
|
RUN /root/.local/bin/uv pip install --system --no-cache git+https://github.com/py-pdf/pypdf.git@c6e43374ab002d76811ec85333fdc2c82c268251
|
|
|
|
WORKDIR /root
|
|
COPY pdelfin pdelfin
|
|
|
|
RUN python3 -m sglang.launch_server --help
|
|
RUN python3 -m pdelfin.beakerpipeline --help |