Dockerfile

FROM python:3.11-slim

# Install build + runtime dependencies in one layer
RUN apt-get update && apt-get install -y \
    git cmake clang build-essential curl libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Clone bitnet.cpp (shallow clone for speed)
RUN git clone --depth 1 --recursive https://github.com/microsoft/BitNet.git /opt/BitNet

# Install BitNet Python deps
RUN pip install --no-cache-dir -r /opt/BitNet/requirements.txt

# Build bitnet.cpp WITHOUT downloading the model (just compile the binary)
# We use cmake directly instead of setup_env.py to avoid the model download
RUN cd /opt/BitNet && \
    cmake -B build -DCMAKE_BUILD_TYPE=Release \
        -DGGML_BITNET_ARM_TL1=OFF \
        -DGGML_BITNET_X86_TL2=OFF && \
    cmake --build build --config Release -j$(nproc) --target llama-server llama-cli

# Create non-root user
RUN useradd -ms /bin/bash user
WORKDIR /home/user/app

# Copy just the binaries we need
RUN cp /opt/BitNet/build/bin/llama-server /home/user/app/ && \
    cp /opt/BitNet/build/bin/llama-cli /home/user/app/ && \
    rm -rf /opt/BitNet

# Install Python app deps
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy app files
COPY app.py start.sh ./
RUN chmod +x start.sh

# Create model directory
RUN mkdir -p /home/user/app/models && \
    chown -R user:user /home/user/app

USER user

EXPOSE 7860

ENV GRADIO_SERVER_NAME="0.0.0.0"
ENV GRADIO_SERVER_PORT="7860"

CMD ["./start.sh"]