Begin work on runpod configuration

tooling/pipeline/runpod/Dockerfile

@@ -0,0 +1,57 @@
+# Phase 1: Pull prebuilt binaries
+FROM ghcr.io/ggml-org/llama.cpp:full-cuda AS llama-bin
+
+# Phase 2: Building environment
+FROM nvidia/cuda:12.6.3-devel-ubuntu24.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+  CMAKE_GENERATOR=Ninja \
+  APP_ROOT=/workspace/app \
+  BUILD_DIR=/workspace/app/build
+
+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 via curl (Ubuntu 24.04 'apt' version can be laggy)
+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
+
+# Copy and link backends
+COPY --from=llama-bin /app/lib*.so* /usr/local/lib/
+RUN ldconfig && \
+  find /usr/local/lib -name "libggml-cuda.so*" -exec ln -s {} /usr/local/lib/libggml-cuda.so \; 2>/dev/null || true && \
+  find /usr/local/lib -name "libggml-cpu.so*" -exec ln -s {} /usr/local/lib/libggml-cpu.so \; 2>/dev/null || true
+
+# Set Environment for the loader
+ENV GGML_BACKEND_PATH="/usr/local/lib"
+ENV LD_LIBRARY_PATH="/usr/local/lib:$LD_LIBRARY_PATH"
+
+# Headers for C++ Build
+RUN git clone --depth 1 -b b9012 https://github.com/ggml-org/llama.cpp.git /tmp/llama-src && \
+  cp -r /tmp/llama-src/include/* /usr/local/include/ && \
+  cp -r /tmp/llama-src/ggml/include/* /usr/local/include/ && \
+  rm -rf /tmp/llama-src
+
+WORKDIR /workspace/app
+COPY . .
+
+# Build the C++ pipeline
+RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
+  cmake --build build -j$(nproc)
+
+# Setup Start Script
+COPY runpod/start.sh /usr/local/bin/biergarten-start
+RUN chmod +x /usr/local/bin/biergarten-start
+
+WORKDIR /workspace/app/build
+ENTRYPOINT ["/usr/local/bin/biergarten-start"]