basic docker image and test

scripts/beaker/Dockerfile-gpu-ci

@@ -0,0 +1,36 @@
+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
+
+
+WORKDIR /root
+
+ENV PYTHONUNBUFFERED=1

scripts/beaker/gpu-ci-script.sh

@@ -0,0 +1,14 @@
+set -ex
+
+git clone git@github.com:allenai/olmocr.git olmocr \
+  && cd olmocr \
+  && git checkout $GIT_REVISION \
+  && /root/.local/bin/uv pip install --system --no-cache . \
+  && /root/.local/bin/uv pip install --system --no-cache sgl-kernel==0.0.3.post1 --force-reinstall --no-deps \
+  && /root/.local/bin/uv pip install --system --no-cache "sglang[all]==0.4.2" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer/
+  && /root/.local/bin/uv pip install --system --no-cache pytest \
+  && python -m olmocr.pipeline ./localworkspace --pdfs tests/gnarly_pdfs/*.pdf \
+  && python tests/gnarly_pdfs/evaluate_gnarly_pdfs.py
+
+
+

tests/gnarly_pdfs/test_gnarly_pdfs.py

@@ -0,0 +1,7 @@
+import unittest
+
+
+class TestGnarlyPdfs(unittest.TestCase):
+    def test_nothing_in_particular(self) -> None:
+        """Noop pending jake's impl"""
+        self.assertTrue(True)