Donato Capitella
77 lines
2.4 KiB
Docker
77 lines
2.4 KiB
Docker
# build stage
|
|
FROM registry.fedoraproject.org/fedora:43 AS builder
|
|
# Toggle llama.cpp PR 15405 (RPC perf for large models)
|
|
ARG APPLY_LLAMA_PR_15405=1
|
|
|
|
# deps
|
|
RUN dnf -y --nodocs --setopt=install_weak_deps=False install \
|
|
git vim \
|
|
make gcc cmake ninja-build lld clang clang-devel compiler-rt libcurl-devel \
|
|
vulkan-loader-devel vulkaninfo mesa-vulkan-drivers \
|
|
radeontop glslc \
|
|
&& dnf clean all && rm -rf /var/cache/dnf/*
|
|
|
|
# llama.cpp
|
|
WORKDIR /opt/llama.cpp
|
|
RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
|
|
|
|
# build
|
|
RUN git clean -xdf \
|
|
&& if [ "${APPLY_LLAMA_PR_15405}" = "1" ]; then \
|
|
echo "Applying llama.cpp PR 15405"; \
|
|
git config user.email "builder@localhost"; \
|
|
git config user.name "Container Builder"; \
|
|
git fetch origin pull/15405/head:pr-15405; \
|
|
git merge --no-edit pr-15405; \
|
|
else \
|
|
echo "Skipping llama.cpp PR 15405"; \
|
|
fi \
|
|
&& git submodule update --recursive \
|
|
&& cmake -S . -B build -G Ninja \
|
|
-DGGML_VULKAN=ON \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DGGML_RPC=ON \
|
|
-DCMAKE_INSTALL_PREFIX=/usr \
|
|
-DLLAMA_BUILD_TESTS=OFF \
|
|
-DLLAMA_BUILD_EXAMPLES=ON \
|
|
-DLLAMA_BUILD_SERVER=ON \
|
|
&& cmake --build build --config Release \
|
|
&& cmake --install build --config Release
|
|
|
|
# libs
|
|
RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
|
|
&& ldconfig
|
|
|
|
# helper
|
|
COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py
|
|
RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
|
|
|
|
|
|
# runtime stage
|
|
FROM registry.fedoraproject.org/fedora-minimal:43
|
|
|
|
# runtime deps
|
|
RUN microdnf -y --nodocs --setopt=install_weak_deps=0 install \
|
|
bash ca-certificates libatomic libstdc++ libgcc \
|
|
vulkan-loader vulkan-loader-devel vulkaninfo mesa-vulkan-drivers radeontop \
|
|
&& microdnf clean all && rm -rf /var/cache/dnf/*
|
|
|
|
# copy
|
|
COPY --from=builder /usr/ /usr/
|
|
COPY --from=builder /usr/local/ /usr/local/
|
|
COPY --from=builder /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/
|
|
|
|
# ld
|
|
RUN echo "/usr/local/lib" > /etc/ld.so.conf.d/local.conf \
|
|
&& echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf \
|
|
&& ldconfig \
|
|
&& cp -n /usr/local/lib/libllama*.so* /usr/lib64/ 2>/dev/null || true \
|
|
&& ldconfig
|
|
|
|
# helper
|
|
COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py
|
|
RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
|
|
|
|
# shell
|
|
CMD ["/bin/bash"]
|