feat: add MTP (Multi-Token Prediction) support via new ROCm 7.2.3 and Vulkan RADV toolboxes

This commit is contained in:
Donato Capitella
2026-05-14 20:09:03 +01:00
parent 7320eb3f00
commit 3e3f3674a8
4 changed files with 186 additions and 1 deletions
+68
View File
@@ -0,0 +1,68 @@
# build stage
FROM registry.fedoraproject.org/fedora:43 AS builder
# 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 \
spirv-headers-devel radeontop glslc patch \
&& dnf clean all && rm -rf /var/cache/dnf/*
# llama.cpp (am17an mtp-clean fork — Multi-Token Prediction)
WORKDIR /opt/llama.cpp
RUN git clone -b mtp-clean --single-branch https://github.com/am17an/llama.cpp.git .
COPY llama-grammar.patch /tmp/llama-grammar.patch
# build
RUN git clean -xdf \
&& git submodule update --recursive \
&& patch -p1 < /tmp/llama-grammar.patch \
&& 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 procps-ng \
&& 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"]