Donato Capitella
62 lines
1.9 KiB
Docker
62 lines
1.9 KiB
Docker
# build stage
|
|
FROM registry.fedoraproject.org/fedora:43 AS builder
|
|
|
|
# deps + rocm toolchain (native fedora packages)
|
|
RUN dnf -y --nodocs --setopt=install_weak_deps=False \
|
|
install \
|
|
make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
|
|
rocminfo radeontop 'rocm-*' 'rocblas-*' hipblas 'hipblas-*' \
|
|
git vim rsync sudo tar xz \
|
|
&& 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 + install
|
|
RUN git clean -xdf \
|
|
&& git submodule update --recursive \
|
|
&& HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
|
|
cmake -S . -B build \
|
|
-DGGML_HIP=ON \
|
|
-DAMDGPU_TARGETS=gfx1151 \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DGGML_RPC=ON \
|
|
-DLLAMA_HIP_UMA=ON \
|
|
&& cmake --build build --config Release -- -j$(nproc) \
|
|
&& cmake --install build --config Release
|
|
|
|
# libs
|
|
RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
|
|
&& ldconfig
|
|
|
|
# runtime stage
|
|
FROM registry.fedoraproject.org/fedora-minimal:43
|
|
|
|
# runtime deps (native fedora rocm + utilities)
|
|
RUN microdnf -y --nodocs --setopt=install_weak_deps=0 \
|
|
install \
|
|
bash ca-certificates libatomic libstdc++ libgcc libgomp sudo \
|
|
rocminfo radeontop 'rocm-*' 'rocblas-*' hipblas 'hipblas-*' \
|
|
procps-ng \
|
|
&& microdnf clean all && rm -rf /var/cache/dnf/*
|
|
|
|
# copy
|
|
COPY --from=builder /usr/local/ /usr/local/
|
|
COPY --from=builder /usr/include/rocwmma /usr/include/rocwmma
|
|
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"]
|