Add local development build support to Docker build system

Extends the Docker Makefile with targets for building from local source code without pushing to GitHub, enabling faster iteration during development.

New build targets:
- build-runtime-local: Build from local source with cache
- build-runtime-local-no-cache: Full rebuild from local source
- build-runtime-no-cache: Force fresh GitHub clone without cache

Added docker/runtime/Dockerfile.local for local source builds, mirroring the GitHub-based Dockerfile structure but using COPY instead of git clone.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

docker/runtime/Dockerfile.local

@@ -0,0 +1,74 @@
+# Ollama37 Runtime Image - Local Development Build
+# Single-stage build: compiles and packages the binary in one image
+# This Dockerfile uses LOCAL source code instead of cloning from GitHub
+# Use this for testing changes without pushing to GitHub
+#
+# Usage: docker build -f docker/runtime/Dockerfile.local -t ollama37:latest .
+#
+# 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
+
+# Copy local source code to container
+# Build context should be the repository root
+COPY . /usr/local/src/ollama37
+
+# 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
+# Build to source directory so binary can find libraries via relative path
+RUN go build -o ./ollama .
+
+# Create symlink to standard binary location
+# The code in ml/path.go uses filepath.EvalSymlinks() which resolves this symlink
+# to /usr/local/src/ollama37/ollama, allowing it to find libraries at build/lib/ollama
+RUN ln -s /usr/local/src/ollama37/ollama /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"]