first commit

2025-11-30 08:06:04 +00:00
commit 82c6e04253
34 changed files with 50959 additions and 0 deletions
@@ -0,0 +1,111 @@
+# build stage
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+# rocm 6.4.3 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-6.4.4]
+name=ROCm6.4.4
+baseurl=https://repo.radeon.com/rocm/el9/6.4.4/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# deps
+RUN dnf -y --nodocs --setopt=install_weak_deps=False \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
+      rocm-llvm rocm-device-libs hip-runtime-amd hip-devel \
+      rocblas rocblas-devel hipblas hipblas-devel \
+      rocminfo radeontop \
+      git-core vim sudo rsync \
+ && dnf clean all && rm -rf /var/cache/dnf/*
+
+# rocm env
+ENV ROCM_PATH=/opt/rocm \
+    HIP_PATH=/opt/rocm \
+    HIP_CLANG_PATH=/opt/rocm/llvm/bin \
+    HIP_DEVICE_LIB_PATH=/opt/rocm/amdgcn/bitcode \
+    PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:$PATH
+
+# llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+# build
+RUN git clean -xdf \
+ && git submodule update --recursive \
+ && cmake -S . -B build \
+      -DGGML_HIP=ON \
+      -DAMDGPU_TARGETS=gfx1201 \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DGGML_RPC=ON \
+      -DLLAMA_HIP_UMA=ON \
+      -DROCM_PATH=/opt/rocm \
+      -DHIP_PATH=/opt/rocm \
+      -DHIP_PLATFORM=amd \
+      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm" \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# libs
+RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
+ && ldconfig
+
+# 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
+
+# rocm 6.4.3 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-6.4.4]
+name=ROCm6.4.4
+baseurl=https://repo.radeon.com/rocm/el9/6.4.4/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# runtime deps
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      bash ca-certificates libatomic libstdc++ libgcc libgomp sudo \
+      hip-runtime-amd rocblas hipblas \
+      rocminfo radeontop \
+ && microdnf clean all && rm -rf /var/cache/dnf/*
+
+# copy
+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
+
+# profile
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# shell
+CMD ["/bin/bash"]
@@ -0,0 +1,127 @@
+# build stage
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+# rocm 6.4.4 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-6.4.4]
+name=ROCm6.4.4
+baseurl=https://repo.radeon.com/rocm/el9/6.4.4/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# deps
+RUN dnf -y --nodocs --setopt=install_weak_deps=False \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      make gcc cmake lld clang clang-devel compiler-rt libcurl-devel ninja-build \
+      rocm-llvm rocm-device-libs hip-runtime-amd hip-devel \
+      rocblas rocblas-devel hipblas hipblas-devel rocm-cmake libomp-devel libomp \
+      rocminfo radeontop \
+      git-core vim sudo rsync \
+ && dnf clean all && rm -rf /var/cache/dnf/*
+
+# rocm env
+ENV ROCM_PATH=/opt/rocm \
+    HIP_PATH=/opt/rocm \
+    HIP_CLANG_PATH=/opt/rocm/llvm/bin \
+    HIP_DEVICE_LIB_PATH=/opt/rocm/amdgcn/bitcode \
+    PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:$PATH
+
+# rocWMMA 
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+# llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+RUN git clean -xdf \
+ && git submodule update --recursive
+
+# overwrite upstream header with our local fixed version
+COPY ggml/src/ggml-cuda/hip_shfl_fix.h /opt/llama.cpp/ggml/src/ggml-cuda/hip_shfl_fix.h
+
+# Apply # rocWMMA patch
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+# Build
+RUN set -euo pipefail \
+ && cmake -S . -B build \
+      -DGGML_HIP=ON \
+      -DAMDGPU_TARGETS=gfx1201 \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DGGML_RPC=ON \
+      -DLLAMA_HIP_UMA=ON \
+      -DGGML_HIP_ROCWMMA_FATTN=ON \
+      -DROCM_PATH=/opt/rocm \
+      -DHIP_PATH=/opt/rocm \
+      -DHIP_PLATFORM=amd \
+      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm -include /opt/llama.cpp/ggml/src/ggml-cuda/hip_shfl_fix.h -Wno-macro-redefined" \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+
+# libs
+RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
+ && ldconfig
+
+# 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
+
+# rocm 6.4.3 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-6.4.4]
+name=ROCm6.4.4
+baseurl=https://repo.radeon.com/rocm/el9/6.4.4/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# runtime deps
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      bash ca-certificates libatomic libstdc++ libgcc libgomp sudo \
+      hip-runtime-amd rocblas hipblas \
+      rocminfo radeontop \
+ && microdnf clean all && rm -rf /var/cache/dnf/*
+
+# copy
+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
+
+# profile
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# shell
+CMD ["/bin/bash"]
@@ -0,0 +1,125 @@
+# build
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+RUN dnf -y --nodocs --setopt=install_weak_deps=False install \
+  make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
+  radeontop git vim patch curl ninja-build tar xz aria2c \
+  && dnf clean all && rm -rf /var/cache/dnf/*
+
+# find & fetch the latest Linux 7.x.x tarball (gfx1151)
+WORKDIR /tmp
+ARG ROCM_MAJOR_VER=7
+ARG GFX=gfx120X-all
+RUN set -euo pipefail; \
+  BASE="https://therock-nightly-tarball.s3.amazonaws.com"; \
+  PREFIX="therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}"; \
+  KEY="$(curl -s "${BASE}?list-type=2&prefix=${PREFIX}" \
+  | tr '<' '\n' \
+  | grep -o "therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}\..*\.tar\.gz" \
+  | sort -V | tail -n1)"; \
+  echo "Latest tarball: ${KEY}"; \
+  aria2c -x 16 -s 16 -j 16 --file-allocation=none "${BASE}/${KEY}" -o therock.tar.gz
+RUN mkdir -p /opt/rocm-7.0 \
+  && tar xzf therock.tar.gz -C /opt/rocm-7.0 --strip-components=1
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+  && git clean -xdf \
+  && git submodule update --recursive
+
+RUN cmake -S . -B build \
+  -DGGML_HIP=ON \
+  -DAMDGPU_TARGETS=gfx1201 \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DGGML_RPC=ON \
+  -DLLAMA_HIP_UMA=ON \
+  && cmake --build build --config Release -- -j$(nproc) \
+  && cmake --install build --config Release
+
+# keep bin; drop headers/docs/static libs (retain llama.cpp for rpc binaries)
+RUN find /opt/rocm-7.0 -type f -name '*.a' -delete \
+  && rm -rf /opt/rocm-7.0/include /opt/rocm-7.0/share \
+  /opt/rocm-7.0/llvm/include /opt/rocm-7.0/llvm/share
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:43
+
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 install \
+  bash ca-certificates libatomic libstdc++ libgcc radeontop vim \
+  && microdnf clean all && rm -rf /var/cache/dnf/*
+
+COPY --from=builder /opt/rocm-7.0 /opt/rocm-7.0
+COPY --from=builder /usr/local/ /usr/local/
+COPY --from=builder /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/
+
+COPY gguf-vram-estimator.py /usr/local/bin/
+RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# make /usr/local libs visible without touching env
+RUN echo "/usr/local/lib"  > /etc/ld.so.conf.d/local.conf \
+  && echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf \
+  && ldconfig
+
+CMD ["/bin/bash"]
@@ -0,0 +1,126 @@
+# build
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+RUN dnf -y --nodocs --setopt=install_weak_deps=False install \
+  make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
+  radeontop git vim patch curl ninja-build tar xz aria2c \
+  && dnf clean all && rm -rf /var/cache/dnf/*
+
+# find & fetch the latest Linux 7.x.x tarball (gfx1151)
+WORKDIR /tmp
+ARG ROCM_MAJOR_VER=7
+ARG GFX=gfx120X-all
+RUN set -euo pipefail; \
+  BASE="https://therock-nightly-tarball.s3.amazonaws.com"; \
+  PREFIX="therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}"; \
+  KEY="$(curl -s "${BASE}?list-type=2&prefix=${PREFIX}" \
+  | tr '<' '\n' \
+  | grep -o "therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}\..*\.tar\.gz" \
+  | sort -V | tail -n1)"; \
+  echo "Latest tarball: ${KEY}"; \
+  aria2c -x 16 -s 16 -j 16 --file-allocation=none "${BASE}/${KEY}" -o therock.tar.gz
+RUN mkdir -p /opt/rocm-7.0 \
+  && tar xzf therock.tar.gz -C /opt/rocm-7.0 --strip-components=1
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+  && git clean -xdf \
+  && git submodule update --recursive
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+RUN cmake -S . -B build \
+  -DGGML_HIP=ON \
+  -DAMDGPU_TARGETS=gfx1201 \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DGGML_RPC=ON \
+  -DGGML_HIP_ROCWMMA_FATTN=ON \
+  && cmake --build build --config Release -- -j$(nproc) \
+  && cmake --install build --config Release
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:43
+
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 install \
+  bash ca-certificates libatomic libstdc++ libgcc radeontop vim \
+  && microdnf clean all && rm -rf /var/cache/dnf/*
+
+COPY --from=builder /opt/rocm-7.0 /opt/rocm-7.0
+COPY --from=builder /usr/local/ /usr/local/
+COPY --from=builder /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/
+
+COPY gguf-vram-estimator.py /usr/local/bin/
+RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# make /usr/local libs visible without touching env
+RUN echo "/usr/local/lib"  > /etc/ld.so.conf.d/local.conf \
+  && echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf \
+  && ldconfig
+
+CMD ["/bin/bash"]
@@ -0,0 +1,111 @@
+# build stage
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+# rocm 7.1 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-7.1]
+name=ROCm7.1
+baseurl=https://repo.radeon.com/rocm/el9/7.1/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# deps
+RUN dnf -y --nodocs --setopt=install_weak_deps=False \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      make gcc cmake lld clang clang-devel compiler-rt libcurl-devel ninja-build \
+      rocm-llvm rocm-device-libs hip-runtime-amd hip-devel \
+      rocblas rocblas-devel hipblas hipblas-devel rocm-cmake libomp-devel libomp \
+      rocminfo radeontop \
+      git-core vim sudo rsync \
+ && dnf clean all && rm -rf /var/cache/dnf/*
+
+# rocm env
+ENV ROCM_PATH=/opt/rocm \
+    HIP_PATH=/opt/rocm \
+    HIP_CLANG_PATH=/opt/rocm/llvm/bin \
+    HIP_DEVICE_LIB_PATH=/opt/rocm/amdgcn/bitcode \
+    PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:$PATH
+
+    # llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+# build
+RUN git clean -xdf \
+ && git submodule update --recursive \
+ && cmake -S . -B build \
+      -DGGML_HIP=ON \
+      -DAMDGPU_TARGETS=gfx1201 \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DGGML_RPC=ON \
+      -DLLAMA_HIP_UMA=ON \
+      -DGGML_CUDA_ENABLE_UNIFIED_MEMORY=ON \
+      -DROCM_PATH=/opt/rocm \
+      -DHIP_PATH=/opt/rocm \
+      -DHIP_PLATFORM=amd \
+      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm" \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# libs
+RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
+ && ldconfig
+
+# 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
+
+# rocm 7.1 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-7.1]
+name=ROCm7.1
+baseurl=https://repo.radeon.com/rocm/el9/7.1/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# runtime deps
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      bash ca-certificates libatomic libstdc++ libgcc libgomp sudo \
+      hip-runtime-amd rocblas hipblas \
+      rocminfo radeontop \
+ && microdnf clean all && rm -rf /var/cache/dnf/*
+
+# copy
+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
+
+# profile
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# shell
+CMD ["/bin/bash"]
@@ -0,0 +1,122 @@
+# build stage
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+# rocm 7.1 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-7.1]
+name=ROCm7.1
+baseurl=https://repo.radeon.com/rocm/el9/7.1/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# deps
+RUN dnf -y --nodocs --setopt=install_weak_deps=False \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      make gcc cmake lld clang clang-devel compiler-rt libcurl-devel ninja-build \
+      rocm-llvm rocm-device-libs hip-runtime-amd hip-devel \
+      rocblas rocblas-devel hipblas hipblas-devel rocm-cmake libomp-devel libomp \
+      rocminfo radeontop \
+      git-core vim sudo rsync \
+ && dnf clean all && rm -rf /var/cache/dnf/*
+
+# rocm env
+ENV ROCM_PATH=/opt/rocm \
+    HIP_PATH=/opt/rocm \
+    HIP_CLANG_PATH=/opt/rocm/llvm/bin \
+    HIP_DEVICE_LIB_PATH=/opt/rocm/amdgcn/bitcode \
+    PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:$PATH
+
+# rocWMMA 
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+# llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+# Apply # rocWMMA patch
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+# build
+RUN git clean -xdf \
+ && git submodule update --recursive \
+ && cmake -S . -B build \
+      -DGGML_HIP=ON \
+      -DAMDGPU_TARGETS=gfx1201 \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DGGML_RPC=ON \
+      -DLLAMA_HIP_UMA=ON \
+      -DGGML_CUDA_ENABLE_UNIFIED_MEMORY=ON \
+      -DGGML_HIP_ROCWMMA_FATTN=ON \
+      -DROCM_PATH=/opt/rocm \
+      -DHIP_PATH=/opt/rocm \
+      -DHIP_PLATFORM=amd \
+      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm" \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# libs
+RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
+ && ldconfig
+
+# 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
+
+# rocm 7.1 repo
+RUN <<'EOF'
+tee /etc/yum.repos.d/rocm.repo <<REPO
+[ROCm-7.1]
+name=ROCm7.1
+baseurl=https://repo.radeon.com/rocm/el9/7.1/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+REPO
+EOF
+
+# runtime deps
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 \
+    --exclude='*sdk*' --exclude='*samples*' --exclude='*-doc*' --exclude='*-docs*' \
+    install \
+      bash ca-certificates libatomic libstdc++ libgcc libgomp sudo \
+      hip-runtime-amd rocblas hipblas \
+      rocminfo radeontop \
+ && microdnf clean all && rm -rf /var/cache/dnf/*
+
+# copy
+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
+
+# profile
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# shell
+CMD ["/bin/bash"]
@@ -0,0 +1,124 @@
+# build
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+RUN dnf -y --nodocs --setopt=install_weak_deps=False install \
+       make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
+       radeontop git vim patch curl ninja-build tar xz aria2c \
+    && dnf clean all && rm -rf /var/cache/dnf/*
+
+# find & fetch the latest Linux 7.x.x rc tarball (gfx1151)
+WORKDIR /tmp
+ARG ROCM_MAJOR_VER=7
+ARG GFX=gfx120X-all
+RUN set -euo pipefail; \
+    BASE="https://therock-nightly-tarball.s3.amazonaws.com"; \
+    PREFIX="therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}"; \
+    KEY="$(curl -s "${BASE}?list-type=2&prefix=${PREFIX}" \
+      | grep -o "therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}\.[0-9]\+\.[0-9]\+rc[0-9]\{8\}\.tar\.gz" \
+      | sort | tail -n1)"; \
+    echo "Latest tarball: ${KEY}"; \
+    aria2c -x 16 -s 16 -j 16 --file-allocation=none "${BASE}/${KEY}" -o therock.tar.gz
+RUN mkdir -p /opt/rocm-7.0 \
+ && tar xzf therock.tar.gz -C /opt/rocm-7.0 --strip-components=1
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+    HIP_PLATFORM=amd \
+    HIP_PATH=/opt/rocm-7.0 \
+    HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+    HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+    HIP_LIB_PATH=/opt/rocm-7.0/lib \
+    HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+    PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+    LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+    LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+    CPATH=/opt/rocm-7.0/include \
+    PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+ && git clean -xdf \
+ && git submodule update --recursive
+
+RUN cmake -S . -B build \
+          -DGGML_HIP=ON \
+          -DAMDGPU_TARGETS=gfx1201 \
+          -DCMAKE_BUILD_TYPE=Release \
+          -DGGML_RPC=ON \
+          -DLLAMA_HIP_UMA=ON \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# keep bin; drop headers/docs/static libs (retain llama.cpp for rpc binaries)
+RUN find /opt/rocm-7.0 -type f -name '*.a' -delete \
+ && rm -rf /opt/rocm-7.0/include /opt/rocm-7.0/share \
+          /opt/rocm-7.0/llvm/include /opt/rocm-7.0/llvm/share
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:43
+
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 install \
+      bash ca-certificates libatomic libstdc++ libgcc radeontop vim \
+  && microdnf clean all && rm -rf /var/cache/dnf/*
+
+COPY --from=builder /opt/rocm-7.0 /opt/rocm-7.0
+COPY --from=builder /usr/local/ /usr/local/
+COPY --from=builder /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/
+
+COPY gguf-vram-estimator.py /usr/local/bin/
+RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+    HIP_PLATFORM=amd \
+    HIP_PATH=/opt/rocm-7.0 \
+    HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+    HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+    HIP_LIB_PATH=/opt/rocm-7.0/lib \
+    HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+    PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+    LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+    LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+    CPATH=/opt/rocm-7.0/include \
+    PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# make /usr/local libs visible without touching env
+RUN echo "/usr/local/lib"  > /etc/ld.so.conf.d/local.conf \
+ && echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf \
+ && ldconfig
+
+CMD ["/bin/bash"]
@@ -0,0 +1,126 @@
+# build
+FROM registry.fedoraproject.org/fedora:43 AS builder
+
+RUN dnf -y --nodocs --setopt=install_weak_deps=False install \
+  make gcc cmake lld clang clang-devel compiler-rt libcurl-devel \
+  radeontop git vim patch curl ninja-build tar xz aria2c \
+  && dnf clean all && rm -rf /var/cache/dnf/*
+
+# find & fetch the latest Linux 7.x.x rc tarball (gfx1151)
+WORKDIR /tmp
+ARG ROCM_MAJOR_VER=7
+ARG GFX=gfx120X-all
+RUN set -euo pipefail; \
+  BASE="https://therock-nightly-tarball.s3.amazonaws.com"; \
+  PREFIX="therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}"; \
+  KEY="$(curl -s "${BASE}?list-type=2&prefix=${PREFIX}" \
+  | grep -o "therock-dist-linux-${GFX}-${ROCM_MAJOR_VER}\.[0-9]\+\.[0-9]\+rc[0-9]\{8\}\.tar\.gz" \
+  | sort | tail -n1)"; \
+  echo "Latest tarball: ${KEY}"; \
+  aria2c -x 16 -s 16 -j 16 --file-allocation=none "${BASE}/${KEY}" -o therock.tar.gz
+RUN mkdir -p /opt/rocm-7.0 \
+  && tar xzf therock.tar.gz -C /opt/rocm-7.0 --strip-components=1
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+  && git clean -xdf \
+  && git submodule update --recursive
+
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+RUN cmake -S . -B build \
+  -DGGML_HIP=ON \
+  -DAMDGPU_TARGETS=gfx1201 \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DGGML_RPC=ON \
+  -DGGML_HIP_ROCWMMA_FATTN=ON \
+  && cmake --build build --config Release -- -j$(nproc) \
+  && cmake --install build --config Release
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:43
+
+RUN microdnf -y --nodocs --setopt=install_weak_deps=0 install \
+  bash ca-certificates libatomic libstdc++ libgcc radeontop vim \
+  && microdnf clean all && rm -rf /var/cache/dnf/*
+
+COPY --from=builder /opt/rocm-7.0 /opt/rocm-7.0
+COPY --from=builder /usr/local/ /usr/local/
+COPY --from=builder /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/
+
+COPY gguf-vram-estimator.py /usr/local/bin/
+RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
+
+ENV ROCM_PATH=/opt/rocm-7.0 \
+  HIP_PLATFORM=amd \
+  HIP_PATH=/opt/rocm-7.0 \
+  HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin \
+  HIP_INCLUDE_PATH=/opt/rocm-7.0/include \
+  HIP_LIB_PATH=/opt/rocm-7.0/lib \
+  HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode \
+  PATH=/opt/rocm-7.0/bin:/opt/rocm-7.0/llvm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+  LD_LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64:/opt/rocm-7.0/llvm/lib \
+  LIBRARY_PATH=/opt/rocm-7.0/lib:/opt/rocm-7.0/lib64 \
+  CPATH=/opt/rocm-7.0/include \
+  PKG_CONFIG_PATH=/opt/rocm-7.0/lib/pkgconfig
+
+RUN printf '%s\n' \
+  'export ROCM_PATH=/opt/rocm-7.0' \
+  'export HIP_PLATFORM=amd' \
+  'export HIP_PATH=/opt/rocm-7.0' \
+  'export HIP_CLANG_PATH=/opt/rocm-7.0/llvm/bin' \
+  'export HIP_INCLUDE_PATH=/opt/rocm-7.0/include' \
+  'export HIP_LIB_PATH=/opt/rocm-7.0/lib' \
+  'export HIP_DEVICE_LIB_PATH=/opt/rocm-7.0/lib/llvm/amdgcn/bitcode' \
+  'export PATH="$ROCM_PATH/bin:$HIP_CLANG_PATH:$PATH"' \
+  'export LD_LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64:$ROCM_PATH/llvm/lib"' \
+  'export LIBRARY_PATH="$HIP_LIB_PATH:$ROCM_PATH/lib:$ROCM_PATH/lib64"' \
+  'export CPATH="$HIP_INCLUDE_PATH"' \
+  'export PKG_CONFIG_PATH="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+# make /usr/local libs visible without touching env
+RUN echo "/usr/local/lib"  > /etc/ld.so.conf.d/local.conf \
+  && echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf \
+  && ldconfig
+
+CMD ["/bin/bash"]
@@ -0,0 +1,77 @@
+# 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 \
+      radeontop glslc wget \
+    && dnf clean all && rm -rf /var/cache/dnf/*
+
+# amdvlk
+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 \
+ && dnf -y install /tmp/amdvlk-*.rpm \
+ && rm -f /tmp/amdvlk-*.rpm
+
+# llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+# build
+RUN git clean -xdf \
+ && 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/*
+
+# amdvlk
+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 \
+ && microdnf -y install /tmp/amdvlk-*.rpm \
+ && rm -f /tmp/amdvlk-*.rpm
+
+# 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"]
@@ -0,0 +1,65 @@
+# 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 \
+      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 \
+ && 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"]
@@ -0,0 +1,155 @@
+#!/bin/bash
+
+# apply-rocwmma-fix.sh - Apply rocWMMA compatibility fixes to llama.cpp
+# Usage: ./apply-rocwmma-fix.sh <path-to-llama.cpp-directory>
+# Source: https://github.com/lhl/strix-halo-testing/blob/main/llm-bench/apply-rocwmma-fix.sh
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+LLAMA_DIR="${1:-}"
+
+if [[ -z "$LLAMA_DIR" ]]; then
+    echo "Usage: $0 <path-to-llama.cpp-directory>"
+    echo ""
+    echo "This script applies rocWMMA compatibility fixes to a llama.cpp checkout."
+    echo "The fixes resolve warp synchronization mask type conflicts between"
+    echo "ROCm headers and CUDA-style code when building with GGML_HIP_ROCWMMA_FATTN=ON."
+    echo ""
+    echo "Example:"
+    echo "  $0 ./llama.cpp"
+    echo "  $0 /path/to/your/llama.cpp"
+    exit 1
+fi
+
+if [[ ! -d "$LLAMA_DIR" ]]; then
+    echo "Error: Directory '$LLAMA_DIR' does not exist"
+    exit 1
+fi
+
+if [[ ! -f "$LLAMA_DIR/CMakeLists.txt" ]] || ! grep -q "llama" "$LLAMA_DIR/CMakeLists.txt" 2>/dev/null; then
+    echo "Error: '$LLAMA_DIR' does not appear to be a llama.cpp directory"
+    echo "Expected to find CMakeLists.txt with 'llama' references"
+    exit 1
+fi
+
+VENDOR_HIP_FILE="$LLAMA_DIR/ggml/src/ggml-cuda/vendors/hip.h"
+
+if [[ ! -f "$VENDOR_HIP_FILE" ]]; then
+    echo "Error: HIP vendor header not found at: $VENDOR_HIP_FILE"
+    echo "This script requires a llama.cpp version with HIP support"
+    exit 1
+fi
+
+echo "Applying rocWMMA compatibility fixes to: $LLAMA_DIR"
+echo ""
+
+# Check if fixes are already applied
+if grep -q "GGML_HIP_WARP_MASK" "$VENDOR_HIP_FILE" 2>/dev/null; then
+    echo "rocWMMA fixes appear to already be applied (found GGML_HIP_WARP_MASK)"
+    echo "To reapply, please first revert changes and run this script again"
+    exit 0
+fi
+
+echo "Step 1: Modifying HIP vendor header..."
+
+# Backup the original file
+cp "$VENDOR_HIP_FILE" "$VENDOR_HIP_FILE.backup"
+
+# Find the line with __shfl_sync and __shfl_xor_sync definitions
+SHFL_LINE=$(grep -n "^#define __shfl_sync" "$VENDOR_HIP_FILE" | head -1 | cut -d: -f1)
+
+if [[ -z "$SHFL_LINE" ]]; then
+    echo "Error: Could not find __shfl_sync macro definition in $VENDOR_HIP_FILE"
+    echo "This script may need updates for this version of llama.cpp"
+    exit 1
+fi
+
+# Create a temporary file with the fix
+{
+    # Print lines before the __shfl_sync definition
+    head -n $((SHFL_LINE - 1)) "$VENDOR_HIP_FILE"
+    
+    # Add our conditional compilation block
+    cat << 'EOF'
+#ifdef GGML_HIP_ROCWMMA_FATTN
+// ROCm requires 64-bit masks for __shfl_*_sync functions
+#define GGML_HIP_WARP_MASK 0xFFFFFFFFFFFFFFFFULL
+#else
+#define __shfl_sync(mask, var, laneMask, width) __shfl(var, laneMask, width)
+#define __shfl_xor_sync(mask, var, laneMask, width) __shfl_xor(var, laneMask, width)
+#define GGML_HIP_WARP_MASK 0xFFFFFFFF
+#endif
+EOF
+    
+    # Skip the original __shfl_sync and __shfl_xor_sync lines and print the rest
+    tail -n +$((SHFL_LINE + 2)) "$VENDOR_HIP_FILE"
+    
+} > "$VENDOR_HIP_FILE.tmp"
+
+mv "$VENDOR_HIP_FILE.tmp" "$VENDOR_HIP_FILE"
+
+echo "  ✓ Added conditional GGML_HIP_WARP_MASK macro to vendor header"
+
+echo ""
+echo "Step 2: Replacing hardcoded warp masks in CUDA files..."
+
+# Find all .cu and .cuh files in the ggml/src/ggml-cuda directory
+CUDA_FILES=($(find "$LLAMA_DIR/ggml/src/ggml-cuda" -name "*.cu" -o -name "*.cuh" 2>/dev/null | sort))
+
+if [[ ${#CUDA_FILES[@]} -eq 0 ]]; then
+    echo "Warning: No CUDA files found in $LLAMA_DIR/ggml/src/ggml-cuda"
+    echo "This may be expected for some llama.cpp versions"
+else
+    MODIFIED_COUNT=0
+    
+    for file in "${CUDA_FILES[@]}"; do
+        # Check if file contains the hardcoded masks
+        if grep -q "0xFFFFFFFF\|0xffffffff" "$file" 2>/dev/null; then
+            # Create backup
+            cp "$file" "$file.backup"
+            
+            # Replace both uppercase and lowercase versions
+            sed -i 's/0xFFFFFFFF/GGML_HIP_WARP_MASK/g; s/0xffffffff/GGML_HIP_WARP_MASK/g' "$file"
+            
+            MODIFIED_COUNT=$((MODIFIED_COUNT + 1))
+            echo "  ✓ Modified: $(basename "$file")"
+        fi
+    done
+    
+    echo "  ✓ Modified $MODIFIED_COUNT CUDA files"
+fi
+
+echo ""
+echo "Step 3: Verification..."
+
+# Verify the vendor header was modified correctly
+if grep -q "GGML_HIP_ROCWMMA_FATTN" "$VENDOR_HIP_FILE" && grep -q "GGML_HIP_WARP_MASK" "$VENDOR_HIP_FILE"; then
+    echo "  ✓ Vendor header modification verified"
+else
+    echo "  ✗ Vendor header modification failed"
+    # Restore backup
+    mv "$VENDOR_HIP_FILE.backup" "$VENDOR_HIP_FILE"
+    echo "  ✓ Restored original vendor header"
+    exit 1
+fi
+
+echo ""
+echo "🎉 rocWMMA compatibility fixes applied successfully!"
+echo ""
+echo "What was changed:"
+echo "  • Added conditional GGML_HIP_WARP_MASK macro to ggml/src/ggml-cuda/vendors/hip.h"
+echo "  • Replaced hardcoded 0xFFFFFFFF/0xffffffff with GGML_HIP_WARP_MASK in CUDA files"
+echo ""
+echo "Behavior:"
+echo "  • For regular HIP builds: GGML_HIP_WARP_MASK = 0xFFFFFFFF (no change)"
+echo "  • For rocWMMA builds: GGML_HIP_WARP_MASK = 0xFFFFFFFFFFFFFFFFULL (64-bit masks)"
+echo ""
+echo "To build with rocWMMA support, use:"
+echo "  cmake -B build -S '$LLAMA_DIR' -DGGML_HIP=ON -DAMDGPU_TARGETS=\"gfx1201\" -DGGML_HIP_ROCWMMA_FATTN=ON"
+echo ""
+echo "Backup files were created with .backup extension in case you need to revert."
+echo ""
+echo "Done! Your llama.cpp checkout now supports rocWMMA builds."
+
+
@@ -0,0 +1,61 @@
+# Source: https://github.com/lhl/strix-halo-testing/blob/main/llm-bench/build-rocwmma.sh
+git clone https://github.com/ROCm/rocWMMA
+cd rocWMMA
+
+# --- BEGIN: make OpenMP explicit for ROCm toolchains (drop-in) ---
+# find libomp (check ROCM_PATH first, then system)
+CANDIDATES=(
+  "${ROCM_PATH}/llvm/lib/libomp.so"
+  "${ROCM_PATH}/llvm/lib/libomp.a"
+  "/usr/lib64/libomp.so"
+  "/usr/lib64/libomp.a"
+  "/usr/local/lib/libomp.so"
+)
+FOUND_LIBOMP=""
+for p in "${CANDIDATES[@]}"; do
+  if [ -f "$p" ]; then
+    FOUND_LIBOMP="$p"
+    break
+  fi
+done
+
+CMAKE_OPTS=""
+if [ -n "$FOUND_LIBOMP" ]; then
+  # directory & basename
+  OMP_LIB_DIR="$(dirname "$FOUND_LIBOMP")"
+  OMP_LIB_BASENAME="$(basename "$FOUND_LIBOMP")"
+  # set cache vars so FindOpenMP will succeed
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_CXX_FLAGS=-fopenmp=libomp"
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_C_FLAGS=-fopenmp=libomp"
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_CXX_LIB_NAMES=omp"
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_C_LIB_NAMES=omp"
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_LIBRARY=${FOUND_LIBOMP}"
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_INCLUDE_DIR=${ROCM_PATH}/llvm/include"
+  export LD_LIBRARY_PATH="${OMP_LIB_DIR}${LD_LIBRARY_PATH:+:}$LD_LIBRARY_PATH"
+  export CXXFLAGS="-fopenmp=libomp ${CXXFLAGS:-}"
+  export LDFLAGS="-L${OMP_LIB_DIR} -lomp ${LDFLAGS:-}"
+else
+  # fallback: force flags so FindOpenMP might at least get flags
+  CMAKE_OPTS="${CMAKE_OPTS} -DOpenMP_CXX_FLAGS=-fopenmp=libomp -DOpenMP_C_FLAGS=-fopenmp=libomp"
+  export CXXFLAGS="-fopenmp=libomp ${CXXFLAGS:-}"
+  export LDFLAGS="${LDFLAGS:-} -lomp"
+fi
+# ---  END: make OpenMP explicit  ---
+
+CC=$ROCM_PATH/llvm/bin/amdclang \
+CXX=$ROCM_PATH/llvm/bin/amdclang++ \
+cmake -B build -S . -G Ninja \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DCMAKE_INSTALL_PREFIX=$ROCM_PATH \
+  -DROCWMMA_BUILD_TESTS=OFF \
+  -DROCWMMA_BUILD_SAMPLES=OFF \
+  -DGPU_TARGETS="gfx1201" \
+  -DOpenMP_CXX_FLAGS="-fopenmp=libomp" \
+  -DOpenMP_C_FLAGS="-fopenmp=libomp" \
+  -DOpenMP_omp_LIBRARY="/usr/lib64/libomp.so" \
+  -DOpenMP_CXX_LIB_NAMES="omp" \
+  -DOpenMP_C_LIB_NAMES="omp" \
+  -DOpenMP_INCLUDE_DIRS="/usr/lib64/clang/19/include"
+
+cmake --install build
+sudo cmake --install build
@@ -0,0 +1,14 @@
+#ifndef HIP_SHFL_FIX_H
+#define HIP_SHFL_FIX_H
+#ifdef __HIP_PLATFORM_AMD__
+  #ifndef __shfl_sync
+    #define __shfl_sync(mask,var,srcLane,width) __shfl((var),(srcLane),(width))
+  #endif
+  #ifndef __shfl_up_sync
+    #define __shfl_up_sync(mask,var,delta,width) __shfl_up((var),(delta),(width))
+  #endif
+  #ifndef __shfl_xor_sync
+    #define __shfl_xor_sync(mask,var,laneMask,width) __shfl_xor((var),(laneMask),(width))
+  #endif
+#endif
+#endif
@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+import sys
+import os
+import re
+import struct
+import argparse
+import math
+from typing import Dict, Any, List
+
+# GGUF constants
+GGUF_MAGIC = 0x46554747
+GGUF_VALUE_TYPE = {
+    0: "UINT8", 1: "INT8", 2: "UINT16", 3: "INT16", 4: "UINT32",
+    5: "INT32", 6: "FLOAT32", 7: "BOOL", 8: "STRING", 9: "ARRAY",
+}
+
+class GGUFMetadataReader:
+    """A minimal reader to get only the necessary KV metadata for cache calculation."""
+    def __init__(self, path: str):
+        self.path = path
+        self.metadata: Dict[str, Any] = {}
+
+    def read(self):
+        with open(self.path, "rb") as f:
+            self.f = f
+            magic, _, _, metadata_kv_count = struct.unpack("<IIQQ", self.f.read(24))
+            if magic != GGUF_MAGIC: raise ValueError("Invalid GGUF magic number")
+            self._read_metadata(metadata_kv_count)
+        return self
+
+    def _read_string(self) -> str:
+        (length,) = struct.unpack("<Q", self.f.read(8))
+        return self.f.read(length).decode("utf-8", errors="replace")
+
+    def _read_value(self, value_type_idx: int):
+        value_type = GGUF_VALUE_TYPE.get(value_type_idx)
+        if not value_type: raise ValueError(f"Unknown GGUF value type: {value_type_idx}")
+        if value_type == "STRING": return self._read_string()
+        if value_type == "UINT32": return struct.unpack("<I", self.f.read(4))[0]
+        if value_type == "INT32": return struct.unpack("<i", self.f.read(4))[0]
+        self._skip_value(value_type_idx)
+
+    def _skip_value(self, value_type_idx: int):
+        value_type = GGUF_VALUE_TYPE.get(value_type_idx)
+        if not value_type: return
+        if value_type in ("UINT8", "INT8", "BOOL"): self.f.seek(1, 1)
+        elif value_type in ("UINT16", "INT16"): self.f.seek(2, 1)
+        elif value_type in ("UINT32", "INT32", "FLOAT32"): self.f.seek(4, 1)
+        elif value_type == "STRING":
+            (length,) = struct.unpack("<Q", self.f.read(8))
+            self.f.seek(length, 1)
+        elif value_type == "ARRAY":
+            (array_type_idx, count) = struct.unpack("<IQ", self.f.read(12))
+            type_map = {0:1, 1:1, 2:2, 3:2, 4:4, 5:4, 6:4, 7:1, 10:8, 11:8, 12:8}
+            element_size = type_map.get(array_type_idx)
+            if element_size: self.f.seek(count * element_size, 1)
+            else:
+                for _ in range(count): self._skip_value(8)
+
+    def _read_metadata(self, count: int):
+        keys_to_read = {"general.architecture", "general.name"}
+        arch_specific_keys_added = False
+        for _ in range(count):
+            key = self._read_string()
+            (value_type_idx,) = struct.unpack("<I", self.f.read(4))
+            if not arch_specific_keys_added and "general.architecture" in self.metadata:
+                prefix = self.metadata["general.architecture"]
+                keys_to_read.update({
+                    f"{prefix}.block_count", f"{prefix}.context_length",
+                    f"{prefix}.attention.head_count_kv", f"{prefix}.attention.key_length",
+                    f"{prefix}.attention.value_length", f"{prefix}.attention.sliding_window_size"
+                })
+                arch_specific_keys_added = True
+            if key in keys_to_read:
+                self.metadata[key] = self._read_value(value_type_idx)
+            else:
+                self._skip_value(value_type_idx)
+
+def get_total_model_size_from_disk(gguf_file_path: str) -> int:
+    """Calculates the total model size by finding all parts on disk."""
+    match = re.search(r'-(\d{5})-of-(\d{5})\.gguf$', gguf_file_path, re.IGNORECASE)
+    if not match:
+        return os.path.getsize(gguf_file_path)
+
+    base_path = gguf_file_path[:match.start()]
+    total_parts_str = match.group(2)
+    total_parts = int(total_parts_str)
+    total_size, found_parts = 0, 0
+    for i in range(1, total_parts + 1):
+        part_file_name = f"{base_path}-{i:05d}-of-{total_parts_str}.gguf"
+        if os.path.exists(part_file_name):
+            total_size += os.path.getsize(part_file_name)
+            found_parts += 1
+    if found_parts != total_parts:
+        print(f"WARNING: Expected {total_parts} parts, found {found_parts}. Size calculation may be incomplete.", file=sys.stderr)
+    return total_size
+
+def format_mem(size_bytes):
+    mib = size_bytes / (1024 * 1024)
+    if mib < 1024: return f"{mib:8.2f} MiB"
+    return f"{mib / 1024:8.2f} GiB"
+
+def run_estimator(gguf_file: str, context_sizes: List[int], overhead_gib: float):
+    try:
+        reader = GGUFMetadataReader(gguf_file).read()
+        metadata = reader.metadata
+        prefix = metadata.get("general.architecture")
+        if not prefix: raise KeyError("Could not read 'general.architecture' from model metadata.")
+        
+        model_size_bytes = get_total_model_size_from_disk(gguf_file)
+        overhead_bytes = int(overhead_gib * 1024**3)
+
+        n_layers = metadata[f"{prefix}.block_count"]
+        n_head_kv = metadata[f"{prefix}.attention.head_count_kv"]
+        training_context = metadata.get(f"{prefix}.context_length", 0)
+        n_embd_head_k = metadata[f"{prefix}.attention.key_length"]
+        n_embd_head_v = metadata[f"{prefix}.attention.value_length"]
+        swa_window_size = metadata.get(f"{prefix}.attention.sliding_window_size", 0)
+        
+        is_scout_model = "scout" in metadata.get("general.name", "").lower()
+        if is_scout_model and swa_window_size == 0: n_layers_swa, n_layers_full, swa_window_size = 36, 12, 8192
+        elif swa_window_size > 0: n_layers_swa, n_layers_full = n_layers, 0
+        else: n_layers_swa, n_layers_full = 0, n_layers
+
+        print(f"\n--- Model '{metadata.get('general.name', 'N/A')}' ---")
+        if training_context > 0: print(f"Max Context: {training_context:,} tokens")
+        print(f"Model Size: {format_mem(model_size_bytes).strip()} (from file size)")
+        print(f"Incl. Overhead: {overhead_gib:.2f} GiB (for compute buffer, etc. adjustable via --overhead)")
+        
+        if training_context > 0:
+            context_sizes = sorted(list(set([c for c in context_sizes if c <= training_context] + [c for c in [training_context] if c not in context_sizes])))
+        else: context_sizes = sorted(context_sizes)
+        
+        bytes_per_token_per_layer = n_head_kv * (n_embd_head_k + n_embd_head_v) * 2
+        
+        print("\n--- Memory Footprint Estimation ---")
+        print(f"{'Context Size':>15s} | {'Context Memory':>15s} | {'Est. Total VRAM':>15s}")
+        print("-" * 51)
+        for n_ctx in context_sizes:
+            mem_full = n_ctx * n_layers_full * bytes_per_token_per_layer
+            mem_swa = min(n_ctx, swa_window_size) * n_layers_swa * bytes_per_token_per_layer
+            kv_cache_bytes = mem_full + mem_swa
+            total_bytes = model_size_bytes + kv_cache_bytes + overhead_bytes
+            print(f"{n_ctx:>15,} | {format_mem(kv_cache_bytes):>15s} | {format_mem(total_bytes):>15s}")
+            
+    except (FileNotFoundError, ValueError, struct.error, NotImplementedError, KeyError) as e:
+        print(f"\nError: {e}", file=sys.stderr)
+        sys.exit(1)
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Calculate VRAM requirements for a GGUF model, including a configurable overhead for compute buffers.",
+        formatter_class=argparse.RawTextHelpFormatter
+    )
+    parser.add_argument("gguf_file", help="Path to the GGUF model file (any part of a multi-part model).")
+    parser.add_argument("-c", "--contexts", nargs='+', type=int, default=[4096, 8192, 16384, 32768, 65536, 131072, 262144, 524288, 1048576], help="Space-separated list of context sizes to calculate.")
+    parser.add_argument("--overhead", type=float, default=2.0, help="Estimated overhead in GiB for compute buffers, drivers, etc. (default: 2.0)")
+    args = parser.parse_args()
+    run_estimator(args.gguf_file, args.contexts, args.overhead)
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,28 @@
+diff --git a/ggml/src/ggml-cuda/vendors/hip.h b/ggml/src/ggml-cuda/vendors/hip.h
+index 8b172e60..b813f523 100644
+--- a/ggml/src/ggml-cuda/vendors/hip.h
+++ b/ggml/src/ggml-cuda/vendors/hip.h
+@@ -137,19 +137,11 @@
+ #define CUBLAS_STATUS_INTERNAL_ERROR HIPBLAS_STATUS_INTERNAL_ERROR
+ #define CUBLAS_STATUS_NOT_SUPPORTED HIPBLAS_STATUS_NOT_SUPPORTED
+ 
+-#if HIP_VERSION >= 70000000
+-#define CUBLAS_COMPUTE_16F HIPBLAS_COMPUTE_16F
+-#define CUBLAS_COMPUTE_32F HIPBLAS_COMPUTE_32F
+#define CUBLAS_COMPUTE_16F         HIPBLAS_COMPUTE_16F
+#define CUBLAS_COMPUTE_32F         HIPBLAS_COMPUTE_32F
+ #define CUBLAS_COMPUTE_32F_FAST_16F HIPBLAS_COMPUTE_32F_FAST_16F
+-#define cublasComputeType_t hipblasComputeType_t
+-#define cudaDataType_t hipDataType
+-#else
+-#define CUBLAS_COMPUTE_16F HIPBLAS_R_16F
+-#define CUBLAS_COMPUTE_32F HIPBLAS_R_32F
+-#define CUBLAS_COMPUTE_32F_FAST_16F HIPBLAS_R_32F
+-#define cublasComputeType_t hipblasDatatype_t
+-#define cudaDataType_t hipblasDatatype_t
+-#endif // HIP_VERSION >= 7000000
+#define cublasComputeType_t        hipblasComputeType_t
+#define cudaDataType_t             hipDataType
+ 
+ #if !defined(__HIP_PLATFORM_AMD__)
+ #error "The HIP backend supports only AMD targets"