diff --git a/.github/workflows/build_and_publish.yml b/.github/workflows/build_and_publish.yml
index fde3015..0d6b0a8 100644
--- a/.github/workflows/build_and_publish.yml
+++ b/.github/workflows/build_and_publish.yml
@@ -28,7 +28,7 @@ jobs:
           IN='${{ inputs.backends }}'
 
           if [[ "$IN" == "all" || -z "$IN" ]]; then
-            JSON='["rocm-6.4.4","rocm-6.4.4-rocwmma","rocm-7rc","rocm-7rc-rocwmma","rocm-7.1-rocwmma","vulkan-amdvlk","vulkan-radv"]'
+            JSON='["rocm-6.4.4","rocm-6.4.4-rocwmma","rocm-7.1","rocm-7.1-rocwmma","rocm-7alpha","rocm-7alpha-rocwmma","rocm-7alpha-rocwmma-improved","rocm-7rc","rocm-7rc-rocwmma","vulkan-amdvlk","vulkan-radv"]'
           else
             # Remove spaces and build JSON array from comma list
             IN_CLEAN=$(echo "$IN" | tr -d '[:space:]')
diff --git a/.github/workflows/prune-old-toolboxes.yml b/.github/workflows/prune-old-toolboxes.yml
index 775b45d..f7c79fe 100644
--- a/.github/workflows/prune-old-toolboxes.yml
+++ b/.github/workflows/prune-old-toolboxes.yml
@@ -44,7 +44,7 @@ jobs:
         run: |
           IN='${{ github.event.inputs.backends }}'
           if [[ "$IN" == "all" || -z "$IN" ]]; then
-            JSON='["rocm-6.4.2","rocm-6.4.2-rocwmma","rocm-6.4.3","rocm-6.4.3-rocwmma","rocm-6.4.4-rocwmma","rocm-7beta","rocm-7rc","rocm-7rc-rocwmma","rocm-7.1-rocwmma","rocm-7rc-rocwmma-fa_all_quants","vulkan-amdvlk","vulkan-radv"]'
+            JSON='["rocm-6.4.2","rocm-6.4.2-rocwmma","rocm-6.4.3","rocm-6.4.3-rocwmma","rocm-6.4.4-rocwmma","rocm-7.1","rocm-7.1-rocwmma","rocm-7beta","rocm-7alpha","rocm-7alpha-rocwmma","rocm-7alpha-rocwmma-improved","rocm-7rc","rocm-7rc-rocwmma","rocm-7rc-rocwmma-fa_all_quants","vulkan-amdvlk","vulkan-radv"]'
           else
             IN_CLEAN=$(echo "$IN" | tr -d '[:space:]')
             JSON='["'${IN_CLEAN//,/\",\"}'"]'
diff --git a/README.md b/README.md
index 97769b1..b5ae284 100644
--- a/README.md
+++ b/README.md
@@ -145,7 +145,7 @@ Once inside, the following commands show how to run local LLMs:
 
 * `llama-cli --list-devices`
   *Lists available GPU devices for Llama.cpp.*
-* `llama-cli --no-mmap -ngl 999 -fa -m <model>`
+* `llama-cli --no-mmap -ngl 999 -fa 1 -m <model>`
   *Runs inference on the specified model, with all layers on GPU and flash attention enabled (replace \*\* with your model path).*
 
 ## 2.3 Downloading GGUF Models from HuggingFace
diff --git a/refresh-toolboxes.sh b/refresh-toolboxes.sh
index 9a4dbdd..47eec80 100755
--- a/refresh-toolboxes.sh
+++ b/refresh-toolboxes.sh
@@ -9,8 +9,13 @@ TOOLBOXES["llama-vulkan-amdvlk"]="docker.io/kyuz0/amd-strix-halo-toolboxes:vulka
 TOOLBOXES["llama-vulkan-radv"]="docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv --device /dev/dri --group-add video --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-6.4.4"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.4 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-6.4.4-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.4-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7.1"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.1 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7.1-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.1-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-7rc"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7rc --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-7rc-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7rc-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7alpha"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7alpha --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7alpha-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7alpha-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7alpha-rocwmma-improved"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7alpha-rocwmma-improved --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 
 function usage() {
   echo "Usage: $0 [all|toolbox-name1 toolbox-name2 ...]"
diff --git a/toolboxes/Dockerfile.rocm-6.4.4-rocwmma b/toolboxes/Dockerfile.rocm-6.4.4-rocwmma
index cb44de3..ba977f6 100644
--- a/toolboxes/Dockerfile.rocm-6.4.4-rocwmma
+++ b/toolboxes/Dockerfile.rocm-6.4.4-rocwmma
@@ -41,17 +41,15 @@ RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
 WORKDIR /opt/llama.cpp
 RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
 
+# 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 git clean -xdf \
- && git pull \
- && git submodule update --recursive \
- && echo -e '#ifndef HIP_HAS_SHFL_SYNC_FUNCS\n#define HIP_HAS_SHFL_SYNC_FUNCS\n#ifndef __shfl_sync\n#define __shfl_sync(mask,var,srcLane,width) __shfl(var,srcLane,width)\n#endif\n#ifndef __shfl_xor_sync\n#define __shfl_xor_sync(mask,var,laneMask,width) __shfl_xor(var,laneMask,width)\n#endif\n#ifndef __shfl_up_sync\n#define __shfl_up_sync(mask,var,delta,width) __shfl_up(var,delta,width)\n#endif\n#endif\n' \
-    | cat - /opt/llama.cpp/ggml/src/ggml-cuda/mma.cuh > /opt/llama.cpp/ggml/src/ggml-cuda/mma.cuh.tmp \
- && mv /opt/llama.cpp/ggml/src/ggml-cuda/mma.cuh.tmp /opt/llama.cpp/ggml/src/ggml-cuda/mma.cuh \
+# Build
+RUN set -euo pipefail \
  && cmake -S . -B build \
       -DGGML_HIP=ON \
       -DAMDGPU_TARGETS=gfx1151 \
@@ -61,10 +59,11 @@ RUN git clean -xdf \
       -DROCM_PATH=/opt/rocm \
       -DHIP_PATH=/opt/rocm \
       -DHIP_PLATFORM=amd \
-      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm" \
+      -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
diff --git a/toolboxes/Dockerfile.rocm-7.1 b/toolboxes/Dockerfile.rocm-7.1
new file mode 100644
index 0000000..63c14a9
--- /dev/null
+++ b/toolboxes/Dockerfile.rocm-7.1
@@ -0,0 +1,111 @@
+# build stage
+FROM registry.fedoraproject.org/fedora:rawhide 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:$PATH
+
+    # llama.cpp
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git .
+
+# build
+RUN git clean -xdf \
+ && git pull \
+ && git submodule update --recursive \
+ && cmake -S . -B build \
+      -DGGML_HIP=ON \
+      -DAMDGPU_TARGETS=gfx1151 \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DLLAMA_HIP_UMA=ON \
+      -DGGML_CUDA_ENABLE_UNIFIED_MEMORY=ON \
+      -DROCM_PATH=/opt/rocm \
+      -DHIP_PATH=/opt/rocm \
+      -DHIP_PLATFORM=amd \
+      -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm" \
+ && cmake --build build --config Release -- -j$(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:rawhide
+
+# 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/
+
+# 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"]
+
diff --git a/toolboxes/Dockerfile.rocm-7alpha b/toolboxes/Dockerfile.rocm-7alpha
new file mode 100644
index 0000000..b6bd81e
--- /dev/null
+++ b/toolboxes/Dockerfile.rocm-7alpha
@@ -0,0 +1,124 @@
+# build
+FROM registry.fedoraproject.org/fedora:rawhide 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=gfx1151
+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="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+ && git clean -xdf \
+ && git submodule update --recursive
+
+RUN cmake -S . -B build \
+          -DGGML_HIP=ON \
+          -DAMDGPU_TARGETS=gfx1151 \
+          -DCMAKE_BUILD_TYPE=Release \
+          -DLLAMA_HIP_UMA=ON \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# keep bin; drop headers/docs/static libs; drop source tree
+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 \
+ && rm -rf /opt/llama.cpp
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:rawhide
+
+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 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"]
diff --git a/toolboxes/Dockerfile.rocm-7alpha-rocwmma b/toolboxes/Dockerfile.rocm-7alpha-rocwmma
new file mode 100644
index 0000000..3f3a795
--- /dev/null
+++ b/toolboxes/Dockerfile.rocm-7alpha-rocwmma
@@ -0,0 +1,126 @@
+# build
+FROM registry.fedoraproject.org/fedora:rawhide 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=gfx1151
+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="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/ggerganov/llama.cpp.git . \
+ && git clean -xdf \
+ && git submodule update --recursive
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+RUN cmake -S . -B build \
+          -DGGML_HIP=ON \
+          -DAMDGPU_TARGETS=gfx1151 \
+          -DCMAKE_BUILD_TYPE=Release \
+          -DGGML_RPC=ON \
+          -DGGML_HIP_ROCWMMA_FATTN=ON \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:rawhide
+
+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"]
diff --git a/toolboxes/Dockerfile.rocm-7alpha-rocwmma-improved b/toolboxes/Dockerfile.rocm-7alpha-rocwmma-improved
new file mode 100644
index 0000000..b34dbf2
--- /dev/null
+++ b/toolboxes/Dockerfile.rocm-7alpha-rocwmma-improved
@@ -0,0 +1,126 @@
+# build
+FROM registry.fedoraproject.org/fedora:rawhide 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=gfx1151
+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="$ROCM_PATH/lib/pkgconfig"' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
+WORKDIR /opt
+COPY ./build-rocwmma.sh .
+RUN chmod +x build-rocwmma.sh && ./build-rocwmma.sh
+
+WORKDIR /opt/llama.cpp
+RUN git clone --recursive https://github.com/hjc4869/llama.cpp.git . \
+ && git clean -xdf \
+ && git submodule update --recursive
+COPY ./apply-rocwmma-fix.sh /opt/apply-rocwmma-fix.sh
+RUN chmod +x /opt/apply-rocwmma-fix.sh && /opt/apply-rocwmma-fix.sh /opt/llama.cpp
+
+RUN cmake -S . -B build \
+          -DGGML_HIP=ON \
+          -DAMDGPU_TARGETS=gfx1151 \
+          -DCMAKE_BUILD_TYPE=Release \
+          -DGGML_RPC=ON \
+          -DGGML_HIP_ROCWMMA_FATTN=ON \
+ && cmake --build build --config Release -- -j$(nproc) \
+ && cmake --install build --config Release
+
+# runtime
+FROM registry.fedoraproject.org/fedora-minimal:rawhide
+
+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"]
diff --git a/toolboxes/Dockerfile.rocm-7rc-rocwmma b/toolboxes/Dockerfile.rocm-7rc-rocwmma
index 7b6cb8b..15b91fd 100644
--- a/toolboxes/Dockerfile.rocm-7rc-rocwmma
+++ b/toolboxes/Dockerfile.rocm-7rc-rocwmma
@@ -59,7 +59,12 @@ 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
+ && git submodule update --recursive \
+ && 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
+
 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
 
diff --git a/toolboxes/ggml/src/ggml-cuda/hip_shfl_fix.h b/toolboxes/ggml/src/ggml-cuda/hip_shfl_fix.h
new file mode 100644
index 0000000..90bff1a
--- /dev/null
+++ b/toolboxes/ggml/src/ggml-cuda/hip_shfl_fix.h
@@ -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