Begin work on Runpod docker config

tooling/pipeline/runpod/Dockerfile

@@ -0,0 +1,67 @@
+# 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 backends to /usr/local/lib and register with ldconfig so the
+# runtime linker can resolve libllama.so, libggml.so, libggml-base.so etc.
+COPY --from=llama-bin /app/lib*.so* /usr/local/lib/
+RUN ldconfig
+
+# 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/ && \
+  rm -rf /tmp/llama-src.tar.gz /tmp/llama.cpp-b9012
+
+ENV LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
+
+WORKDIR /workspace/app
+COPY . .
+
+# Build the C++ pipeline
+RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
+  cmake --build build -j$(nproc)
+
+# Co-locate GGML backend plugins with the executable.
+# ggml_backend_load_all() searches the executable directory first when
+# GGML_BACKEND_DIR is not set. Copying the ggml-*.so plugin files here
+# ensures the loader finds them without any environment variable.
+
+# libllama.so, libggml.so, and libggml-base.so are NOT copied here —
+# those are proper shared libraries resolved via ldconfig/LD_LIBRARY_PATH.
+RUN cp /usr/local/lib/libggml-cuda.so  /workspace/app/build/ 2>/dev/null || true && \
+  cp /usr/local/lib/libggml-cpu*.so   /workspace/app/build/ 2>/dev/null || true && \
+  cp /usr/local/lib/libggml-blas*.so  /workspace/app/build/ 2>/dev/null || true && \
+  cp /usr/local/lib/libggml-rpc*.so   /workspace/app/build/ 2>/dev/null || true
+
+# 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"]

tooling/pipeline/runpod/README.md

@@ -0,0 +1,8 @@
+```bash
+touch runpod/start.sh
+docker build \
+ --progress=plain \
+ -t biergarten-pipeline:latest \
+ -f runpod/Dockerfile \
+ . 2>&1 | tee build.log
+```

tooling/pipeline/runpod/pod-template.yaml

@@ -0,0 +1,22 @@
+name: biergarten-pipeline-live
+imageName: biergarten-pipeline:latest
+category: NVIDIA
+containerDiskInGb: 50
+volumeInGb: 50
+volumeMountPath: /workspace
+dockerEntrypoint:
+  - /usr/local/bin/biergarten-start
+dockerStartCmd: []
+isPublic: false
+isServerless: false
+env:
+  BIERGARTEN_MODE: live
+  BIERGARTEN_MODEL_PATH: /workspace/models/google_gemma-4-E4B-it-Q6_K.gguf
+  BIERGARTEN_PROMPT_DIR: /workspace/app/build/prompts
+  BIERGARTEN_OUTPUT_DIR: /workspace/output
+  BIERGARTEN_LOG_PATH: /workspace/logs/pipeline.log
+  BIERGARTEN_TEMPERATURE: "1.0"
+  BIERGARTEN_TOP_P: "0.95"
+  BIERGARTEN_TOP_K: "64"
+  BIERGARTEN_N_CTX: "8192"
+  BIERGARTEN_SEED: "-1"

tooling/pipeline/runpod/start.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+set -e
+
+# Configuration / Defaults
+MODEL_PATH="${BIERGARTEN_MODEL_PATH:-/workspace/models/google_gemma-4-E4B-it-Q6_K.gguf}"
+OUTPUT_DIR="${BIERGARTEN_OUTPUT_DIR:-/workspace/output}"
+LOG_PATH="${BIERGARTEN_LOG_PATH:-/workspace/logs/pipeline.log}"
+EXECUTABLE="/workspace/app/build/biergarten-pipeline"
+PROMPT_DIR="/workspace/app/build/prompts"
+
+echo "--- Starting Biergarten Pipeline Environment Check ---"
+
+# 1. Ensure volume mount directories exist
+mkdir -p "$OUTPUT_DIR"
+mkdir -p "$(dirname "$LOG_PATH")"
+
+# 2. Check for model file
+if [ ! -f "$MODEL_PATH" ]; then
+    echo "ERROR: Model not found at $MODEL_PATH"
+    echo "Current /workspace/models contents:"
+    ls -lh /workspace/models 2>/dev/null || echo "(directory does not exist)"
+    exit 1
+fi
+
+# 3. Build the command arguments
+ARGS=(
+    "--model"      "$MODEL_PATH"
+    "--prompt-dir" "$PROMPT_DIR"
+    "--output"     "$OUTPUT_DIR"
+    "--log-path"   "$LOG_PATH"
+)
+
+# Optional hyperparameters
+[[ -n "$BIERGARTEN_TEMPERATURE" ]] && ARGS+=("--temperature"  "$BIERGARTEN_TEMPERATURE")
+[[ -n "$BIERGARTEN_TOP_P" ]]       && ARGS+=("--top-p"        "$BIERGARTEN_TOP_P")
+[[ -n "$BIERGARTEN_TOP_K" ]]       && ARGS+=("--top-k"        "$BIERGARTEN_TOP_K")
+[[ -n "$BIERGARTEN_N_CTX" ]]       && ARGS+=("--n-ctx"        "$BIERGARTEN_N_CTX")
+[[ -n "$BIERGARTEN_SEED" ]]        && ARGS+=("--seed"         "$BIERGARTEN_SEED")
+[[ -n "$BIERGARTEN_GL_LAYERS" ]]   && ARGS+=("--n-gpu-layers" "$BIERGARTEN_GL_LAYERS")
+
+# Append any extra custom args
+if [[ -n "$BIERGARTEN_EXTRA_ARGS" ]]; then
+    ARGS+=($BIERGARTEN_EXTRA_ARGS)
+fi
+
+echo "--- Executing: $EXECUTABLE ${ARGS[*]} ---"
+
+# Execute the binary directly, replacing the shell process
+exec "$EXECUTABLE" "${ARGS[@]}"