Cleanup of vllm perf branch with @amanr

Dockerfile

@@ -1,60 +1,65 @@
 ARG CUDA_VERSION=12.8.1
 FROM --platform=linux/amd64 nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
+
 # Needs to be repeated below the FROM, or else it's not picked up
 ARG PYTHON_VERSION=3.12
 ARG CUDA_VERSION=12.8.1
+
 # Set environment variable to prevent interactive prompts
 ENV DEBIAN_FRONTEND=noninteractive
+
 # From original VLLM dockerfile https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile
 # Install Python and other dependencies
 RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
-&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
-&& apt-get update -y \
-&& apt-get install -y ccache software-properties-common git curl sudo python3-apt \
-&& for i in 1 2 3; do \
-add-apt-repository -y ppa:deadsnakes/ppa && break || \
-{ echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
-done \
-&& apt-get update -y \
-&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv
+    && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
+    && apt-get update -y \
+    && apt-get install -y ccache software-properties-common git curl sudo python3-apt \
+    && for i in 1 2 3; do \
+    add-apt-repository -y ppa:deadsnakes/ppa && break || \
+    { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
+    done \
+    && apt-get update -y \
+    && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv
 
 # olmOCR Specific Installs - Install fonts BEFORE changing Python version
 RUN echo "ttf-mscorefonts-installer msttcorefonts/accepted-mscorefonts-eula select true" | debconf-set-selections && \
-apt-get update -y && \
-apt-get install -y --no-install-recommends poppler-utils fonts-crosextra-caladea fonts-crosextra-carlito gsfonts lcdf-typetools ttf-mscorefonts-installer
+    apt-get update -y && \
+    apt-get install -y --no-install-recommends poppler-utils fonts-crosextra-caladea fonts-crosextra-carlito gsfonts lcdf-typetools ttf-mscorefonts-installer
 
 # Now update Python alternatives
 RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
-&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
-&& update-alternatives --install /usr/bin/python python /usr/bin/python${PYTHON_VERSION} 1 \
-&& update-alternatives --set python /usr/bin/python${PYTHON_VERSION} \
-&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
-&& curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
-&& python3 --version && python3 -m pip --version
+    && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
+    && update-alternatives --install /usr/bin/python python /usr/bin/python${PYTHON_VERSION} 1 \
+    && update-alternatives --set python /usr/bin/python${PYTHON_VERSION} \
+    && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
+    && curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
+    && python3 --version && python3 -m pip --version
 
 # Install uv for faster pip installs
-RUN --mount=type=cache,target=/root/.cache/uv \
-python3 -m pip install uv
+RUN --mount=type=cache,target=/root/.cache/uv python3 -m pip install uv
 
 # Install some helper utilities for things like the benchmark
 RUN apt-get update -y && apt-get install -y --no-install-recommends \
-git \
-git-lfs \
-curl \
-wget \
-unzip
+    git \
+    git-lfs \
+    curl \
+    wget \
+    unzip
+
 ENV PYTHONUNBUFFERED=1
 WORKDIR /root
 COPY pyproject.toml pyproject.toml
 COPY olmocr/version.py olmocr/version.py
+
 # Needed to resolve setuptools dependencies
 ENV UV_INDEX_STRATEGY="unsafe-best-match"
-RUN uv pip install --system --no-cache -e . --extra-index-url https://download.pytorch.org/whl/cu128
-RUN uv pip install --system --no-cache ".[gpu]" --extra-index-url https://download.pytorch.org/whl/cu128
+RUN uv pip install --system --no-cache -e ".[gpu]"  --extra-index-url https://download.pytorch.org/whl/cu128
 RUN uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.5%2Bcu128torch2.7-cp38-abi3-linux_x86_64.whl
 RUN uv pip install --system --no-cache ".[bench]"
 RUN playwright install-deps
 RUN playwright install chromium
+
 COPY olmocr olmocr
 COPY scripts scripts
+
 RUN python3 -m olmocr.pipeline --help

olmocr/pipeline.py

@@ -574,7 +574,6 @@ async def vllm_server_task(model_name_or_path, args, semaphore):
         "--disable-log-requests",
         "--uvicorn-log-level", "warning",
         "--served-model-name", "Qwen/Qwen2-VL-7B-Instruct",
-        "--dtype", args.dtype,
     ]
     cmd.extend(mem_fraction_arg)
 
@@ -987,7 +986,6 @@ async def main():
         help="List of paths where you can find the model to convert this pdf. You can specify several different paths here, and the script will try to use the one which is fastest to access",
         default="allenai/olmOCR-7B-0225-preview",
     )
-    parser.add_argument("--dtype", type=str, default="bfloat16", help="Data type for model weights")
     parser.add_argument("--model_max_context", type=int, default="8192", help="Maximum context length that the model was fine tuned under")
     parser.add_argument("--model_chat_template", type=str, default="qwen2-vl", help="Chat template to pass to vllm server")
     parser.add_argument("--target_longest_image_dim", type=int, help="Dimension on longest side to use for rendering the pdf pages", default=1024)