AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-06-01 01:54:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

reduce docker image size

Browse Source 
Co-authored-by: Copilot <copilot@github.com>
This commit is contained in:
Aaron Po
2026-05-04 23:11:17 -04:00
parent c0445baebc
commit b4238cd713
2 changed files with 43 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
tooling/pipeline/runpod/Dockerfile
View File

@@ -1,44 +1,26 @@
# 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
# --- 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 \
APP_ROOT=/workspace/app \
BUILD_DIR=/workspace/app/build
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 \
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)
# 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
# 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
# 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/ && \
rm -rf /tmp/llama-src.tar.gz /tmp/llama.cpp-b9012
cp -r /tmp/llama.cpp-b9012/ggml/include/* /usr/local/include/
ENV LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
# Pull llama.cpp binaries to use during build if needed
COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
WORKDIR /workspace/app
COPY . .
@@ -47,21 +29,42 @@ COPY . .
RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
cmake --build build -j$(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.
# --- Stage 2: Runtime Environment (The "Slim" Stage) ---
FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04 AS runtime
# 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
# Install only necessary runtime shared libraries
RUN apt-get update && apt-get install -y --no-install-recommends \
libboost-json1.83.0 \
libboost-program-options1.83.0 \
libgomp1 \
libssl3 \
zlib1g \
&& rm -rf /var/lib/apt/lists/*
ENV APP_ROOT=/workspace/app \
LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
WORKDIR /workspace/app/build
# Copy only the compiled binaries from the builder
COPY --from=builder /workspace/app/build/biergarten-pipeline ./
# Copy required config files
COPY locations.json /workspace/app/build/
COPY beer-styles.json /workspace/app/build/
# Copy prompt templates
COPY prompts /workspace/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
WORKDIR /workspace/app/build
ENTRYPOINT ["/usr/local/bin/biergarten-start"]