mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-18 03:37:09 +00:00
738a8ba2da
Corrects misleading architecture description and enhances code comments: - Fix header: change "two-stage build" to accurate "single-stage build" - Remove obsolete multi-stage build artifacts (builder/runtime aliases) - Clarify LD_LIBRARY_PATH purpose during CMake configuration - Document parallel compilation benefit (-j flag) - Explain health check validation scope (API + model registry) - Add specific library path location to header comments This aligns with the CLAUDE.md documentation policy of adding helpful comments to improve code maintainability and debugging experience. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
65 lines
2.6 KiB
Docker
65 lines
2.6 KiB
Docker
# Ollama37 Runtime Image
|
|
# Single-stage build: compiles and packages the binary in one image
|
|
# The runtime needs access to the build directory for GGML CUDA libraries
|
|
# This ensures the compiled binary can find all required runtime libraries at:
|
|
# /usr/local/src/ollama37/build/lib/ollama
|
|
|
|
# Base image: ollama37-builder contains GCC 10, CUDA 11.4, and build tools
|
|
FROM ollama37-builder
|
|
|
|
# Clone ollama37 source code from GitHub
|
|
RUN cd /usr/local/src\
|
|
&& git clone https://github.com/dogkeeper886/ollama37.git
|
|
|
|
# Set working directory for build
|
|
WORKDIR /usr/local/src/ollama37
|
|
|
|
# Configure build with CMake
|
|
# Use "CUDA 11" preset for Tesla K80 compute capability 3.7 support
|
|
# Set LD_LIBRARY_PATH during build so CMake can locate GCC 10 runtime libraries
|
|
# and properly link against them (required for C++ standard library and atomics)
|
|
RUN bash -c 'LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib64:$LD_LIBRARY_PATH \
|
|
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ \
|
|
cmake --preset "CUDA 11"'
|
|
|
|
# Build C/C++/CUDA libraries with CMake
|
|
# Compile all GGML CUDA kernels and Ollama native libraries
|
|
# Use all available CPU cores (-j) for parallel compilation to speed up build
|
|
RUN bash -c 'LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib64:$LD_LIBRARY_PATH \
|
|
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ \
|
|
cmake --build build -j$(nproc)'
|
|
|
|
# Build Go binary
|
|
# VCS info is embedded automatically since we cloned from git
|
|
RUN go build -o /usr/local/bin/ollama .
|
|
|
|
# Setup library paths for runtime
|
|
# The binary expects libraries in these exact paths:
|
|
# /usr/local/src/ollama37/build/lib/ollama - Ollama CUDA/GGML libraries
|
|
# /usr/local/lib64 - GCC 10 runtime libraries (libstdc++, libgcc_s)
|
|
# /usr/local/cuda-11.4/lib64 - CUDA 11.4 runtime libraries
|
|
# /usr/lib64 - System libraries
|
|
ENV LD_LIBRARY_PATH=/usr/local/src/ollama37/build/lib/ollama:/usr/local/lib64:/usr/local/cuda-11.4/lib64:/usr/lib64
|
|
|
|
# Configure Ollama server to listen on all interfaces
|
|
ENV OLLAMA_HOST=0.0.0.0:11434
|
|
|
|
# Expose Ollama API port
|
|
EXPOSE 11434
|
|
|
|
# Create persistent volume for model storage
|
|
# Models downloaded by Ollama will be stored here
|
|
RUN mkdir -p /root/.ollama
|
|
VOLUME ["/root/.ollama"]
|
|
|
|
# Configure health check to verify Ollama is running
|
|
# Uses 'ollama list' command to check if the service is responsive
|
|
# This validates both API availability and model registry access
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
|
|
CMD /usr/local/bin/ollama list || exit 1
|
|
|
|
# Set entrypoint and default command
|
|
# Container runs 'ollama serve' by default to start the API server
|
|
ENTRYPOINT ["/usr/local/bin/ollama"]
|
|
CMD ["serve"]
|