Donato Capitella
38 lines
1.2 KiB
Docker
38 lines
1.2 KiB
Docker
FROM fedora:rawhide
|
|
|
|
# Install build tools, Vulkan headers/loader, and glslc
|
|
RUN dnf install --refresh -y \
|
|
git vim \
|
|
make gcc cmake ninja-build lld clang clang-devel compiler-rt libcurl-devel \
|
|
vulkan-loader-devel vulkaninfo mesa-vulkan-drivers \
|
|
radeontop glslc wget \
|
|
&& dnf clean all
|
|
|
|
# Get AMDVLK drivers
|
|
RUN curl -L -o /tmp/amdvlk-2025.Q2.1.x86_64.rpm \
|
|
https://github.com/GPUOpen-Drivers/AMDVLK/releases/download/v-2025.Q2.1/amdvlk-2025.Q2.1.x86_64.rpm
|
|
RUN dnf install -y /tmp/amdvlk-*.rpm
|
|
|
|
WORKDIR /opt/llama.cpp
|
|
|
|
# Clone llama.cpp
|
|
RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
|
|
|
|
# Build with Vulkan support
|
|
RUN git clean -xdf \
|
|
&& git pull \
|
|
&& git submodule update --recursive \
|
|
&& cmake -S . -B build -G Ninja \
|
|
-DGGML_VULKAN=ON \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-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
|
|
|
|
COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py
|
|
RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
|
|
|
|
CMD ["/bin/bash"] |