Pipeline: Add Runpod docker configuration (#222)

* Begin work on Runpod docker config

* Reduce docker image size

* Create .dockerignore

tooling/pipeline/runpod/Dockerfile

@@ -0,0 +1,72 @@
+# --- Stage 1: Build Environment (The "Heavy" Stage) ---
+FROM nvidia/cuda:12.6.3-devel-ubuntu24.04 AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive \
+  CMAKE_GENERATOR=Ninja
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  build-essential ca-certificates curl git libboost-json-dev \
+  libboost-program-options-dev libssl-dev ninja-build pkg-config zlib1g-dev \
+  && rm -rf /var/lib/apt/lists/*
+
+# Install modern CMake
+RUN curl -L https://github.com/Kitware/CMake/releases/download/v3.31.0/cmake-3.31.0-linux-x86_64.sh -o cmake.sh && \
+  sh cmake.sh --skip-license --prefix=/usr/local && rm cmake.sh
+
+# Get headers for C++ build
+RUN curl -L https://github.com/ggml-org/llama.cpp/archive/refs/tags/b9012.tar.gz -o /tmp/llama-src.tar.gz && \
+  tar -xzf /tmp/llama-src.tar.gz -C /tmp && \
+  cp -r /tmp/llama.cpp-b9012/include/* /usr/local/include/ && \
+  cp -r /tmp/llama.cpp-b9012/ggml/include/* /usr/local/include/
+
+# Pull llama.cpp binaries to use during build if needed
+COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
+
+WORKDIR /app
+COPY . .
+
+# Build the C++ pipeline
+RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
+  cmake --build build -j$(nproc)
+
+# --- Stage 2: Runtime Environment (The "Slim" Stage) ---
+FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04 AS runtime
+
+# Install only necessary runtime shared libraries
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  curl \
+  ca-certificates \
+  libboost-json1.83.0 \
+  libboost-program-options1.83.0 \
+  libgomp1 \
+  libssl3 \
+  zlib1g \
+  && rm -rf /var/lib/apt/lists/*
+
+ENV APP_ROOT=/app \
+  LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
+
+WORKDIR /app/build
+
+# Copy only the compiled binaries from the builder
+COPY --from=builder /app/build/biergarten-pipeline ./
+
+# Copy required config files
+COPY locations.json /app/build/
+COPY beer-styles.json /app/build/
+
+# Copy prompt templates
+COPY prompts /app/prompts
+
+# Copy only the necessary shared libraries from builder/llama-bin
+COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
+
+# Co-locate plugins
+RUN cp /usr/local/lib/libggml-cuda.so . 2>/dev/null || true && \
+  cp /usr/local/lib/libggml-cpu*.so . 2>/dev/null || true
+
+# Setup Start Script
+COPY ./runpod/start.sh /usr/local/bin/biergarten-start
+RUN chmod +x /usr/local/bin/biergarten-start
+
+ENTRYPOINT ["/usr/local/bin/biergarten-start"]