chore: update ROCm version to 7.2.3 and remove deprecated pr21344 toolbox

.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-7.2.2","rocm-7.2.2-pr21344","rocm7-nightlies","vulkan-amdvlk","vulkan-radv"]'
+            JSON='["rocm-6.4.4","rocm-7.2.3","rocm7-nightlies","vulkan-amdvlk","vulkan-radv"]'
           else
             # Remove spaces and build JSON array from comma list
             IN_CLEAN=$(echo "$IN" | tr -d '[:space:]')

.github/workflows/prune-old-toolboxes.yml

@@ -44,7 +44,7 @@ jobs:
         run: |
           IN='${{ github.event.inputs.backends }}'
           if [[ "$IN" == "all" || -z "$IN" ]]; then
-            JSON='["rocm-6.4.2","rocm-6.4.3","rocm-6.4.4","rocm-7.1.1","rocm-7.2","rocm-7.2.1","rocm-7.2.1-pr21344","rocm-7.2.2","rocm-7.2.2-pr21344","rocm-7beta","rocm7-nightlies","vulkan-amdvlk","vulkan-radv"]'
+            JSON='["rocm-6.4.2","rocm-6.4.3","rocm-6.4.4","rocm-7.1.1","rocm-7.2","rocm-7.2.1","rocm-7.2.1-pr21344","rocm-7.2.2","rocm-7.2.3","rocm-7beta","rocm7-nightlies","vulkan-amdvlk","vulkan-radv"]'
           else
             IN_CLEAN=$(echo "$IN" | tr -d '[:space:]')
             JSON='["'${IN_CLEAN//,/\",\"}'"]'

AGENTS.md

@@ -8,7 +8,7 @@
 *   **Hardware / Drivers**: AMD "Strix Halo" APUs (Gfx1151). Implementations depend on ROCm (v6.4.4, v7.x) and Vulkan (Mesa RADV, AMDVLK).
 
 ## Repository Structure Overview
-*   `/toolboxes/`: Dockerfiles used to build the container images (e.g., `rocm-6.4.4`, `rocm-7.2.2`, `vulkan-radv`). These often use multi-stage builds to compile Llama.cpp and extract standalone binaries.
+*   `/toolboxes/`: Dockerfiles used to build the container images (e.g., `rocm-6.4.4`, `rocm-7.2.3`, `vulkan-radv`). These often use multi-stage builds to compile Llama.cpp and extract standalone binaries.
 *   `/benchmark/`: Shell scripts and Python utilities (like `generate_results_json.py`) to systematically test Llama.cpp throughput, latency, and RPC performance.
 *   `/docs/`: Markdown documents, along with HTML/CSS/JS (e.g., `index.html`, `assets/`) for the GitHub Pages website (`strix-halo-toolboxes.com`), plus interactive benchmark viewers and documentation on VRAM estimation.
 *   `/scripts/`: Python utilities, including `run_distributed_llama.py` for distributed inference across nodes.

README.md

@@ -44,7 +44,7 @@ This is currently the most stable setup. Kernels older than 6.18.4 have a bug th
 ## Supported Toolboxes
 
 > [!WARNING]
-> Current `rocm7-nightlies` builds have a bug that caps memory allocation to 64GB. If you need larger models, prefer stable builds like `rocm-7.2.2` (performance is similar). Track the issue here: https://github.com/ROCm/TheRock/issues/4645
+> Current `rocm7-nightlies` builds have a bug that caps memory allocation to 64GB. If you need larger models, prefer stable builds like `rocm-7.2.3` (performance is similar). Track the issue here: https://github.com/ROCm/TheRock/issues/4645
 
 You can check the containers on DockerHub: [kyuz0/amd-strix-halo-toolboxes](https://hub.docker.com/r/kyuz0/amd-strix-halo-toolboxes/tags).
 
@@ -53,7 +53,7 @@ You can check the containers on DockerHub: [kyuz0/amd-strix-halo-toolboxes](http
 | `vulkan-amdvlk` | Vulkan (AMDVLK) | Fastest backend—AMD open-source driver. ≤2 GiB single buffer allocation limit, some large models won't load. |
 | `vulkan-radv` | Vulkan (Mesa RADV) | Most stable and compatible. Recommended for most users and all models. |
 | `rocm-6.4.4` | ROCm 6.4.4 (Fedora 43) | Latest stable 6.x build. Uses Fedora 43 packages with backported patch for **kernel 6.18.4+** support. |
-| `rocm-7.2.2` | ROCm 7.2.2 | Latest stable 7.x build. Includes patch for **kernel 6.18.4+** support. |
+| `rocm-7.2.3` | ROCm 7.2.3 | Latest stable 7.x build. Includes patch for **kernel 6.18.4+** support. |
 | `rocm7-nightlies` | ROCm 7 Nightly | Tracks nightly builds. Includes patch for **kernel 6.18.4+** support. |
 
 > These containers are **automatically** rebuilt whenever the Llama.cpp master branch is updated. Legacy images (`rocm-6.4.2`, `rocm-6.4.3`, `rocm-7.1.1`) are excluded from this list.
@@ -73,12 +73,12 @@ toolbox enter llama-vulkan-radv
 
 **Option B: ROCm (Recommended for Performance)**
 ```sh
-toolbox create llama-rocm-7.2.2 \
+toolbox create llama-rocm-7.2.3 \
-  --image docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.2.2 \
+  --image docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.2.3 \
   -- --device /dev/dri --device /dev/kfd \
   --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined
 
-toolbox enter llama-rocm-7.2.2
+toolbox enter llama-rocm-7.2.3
 ```
 
 ### 2. Check GPU Access

benchmark/run_benchmarks.sh

@@ -62,8 +62,7 @@ echo
 
 declare -A CMDS=(
   [rocm6_4_4]="toolbox run -c llama-rocm-6.4.4 -- /usr/local/bin/llama-bench"
-  [rocm-7_2_2]="toolbox run -c llama-rocm-7.2.2 -- /usr/local/bin/llama-bench"
+  [rocm-7_2_3]="toolbox run -c llama-rocm-7.2.3 -- /usr/local/bin/llama-bench"
-  [rocm-7_2_2-pr21344]="toolbox run -c llama-rocm-7.2.2-pr21344 -- /usr/local/bin/llama-bench"
   [rocm7-nightlies]="toolbox run -c llama-rocm7-nightlies -- /usr/local/bin/llama-bench"
   [vulkan_amdvlk]="toolbox run -c llama-vulkan-amdvlk -- /usr/sbin/llama-bench"
   [vulkan_radv]="toolbox run -c llama-vulkan-radv -- /usr/sbin/llama-bench"

refresh-toolboxes.sh

@@ -8,8 +8,7 @@ declare -A TOOLBOXES
 TOOLBOXES["llama-vulkan-amdvlk"]="docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-amdvlk --device /dev/dri --group-add video --security-opt seccomp=unconfined"
 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-7.2.2"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.2.2 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-7.2.3"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.2.3 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
-TOOLBOXES["llama-rocm-7.2.2-pr21344"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7.2.2-pr21344 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm7-nightlies"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm7-nightlies --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 
 function usage() {

toolboxes/Dockerfile.rocm-7.2.2-pr21344

@@ -1,124 +0,0 @@
-# build stage
-# Based on Dockerfile.rocm-7.2.2, but clones pedapudi/llama.cpp@gfx1151-opt
-# (PR #21344: gfx1151 nwarps, tile sizing to curb VGPR pressure)
-FROM registry.fedoraproject.org/fedora:43 AS builder
-
-# rocm 7.2.2 repo
-RUN <<'EOF'
-tee /etc/yum.repos.d/rocm.repo <<REPO
-[ROCm-7.2.2]
-name=ROCm7.2.2
-baseurl=https://repo.radeon.com/rocm/rhel10/7.2.2/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 patch \
-  && 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 — PR #21344 fork (gfx1151 MMQ/MMVQ tile + nwarp tuning)
-WORKDIR /opt/llama.cpp
-ARG REPO=https://github.com/pedapudi/llama.cpp.git
-ARG BRANCH=gfx1151-opt
-RUN git clone -b ${BRANCH} --single-branch --recursive ${REPO} .
-
-COPY llama-grammar.patch /tmp/llama-grammar.patch
-
-# build
-RUN git clean -xdf \
-  && git submodule update --recursive \
-  && patch -p1 < /tmp/llama-grammar.patch \
-  && cmake -S . -B build \
-  -DGGML_HIP=ON \
-  -DCMAKE_HIP_COMPILER=${HIP_CLANG_PATH}/clang \
-  -DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm -mllvm --amdgpu-unroll-threshold-local=600" \
-  -DAMDGPU_TARGETS=gfx1151 \
-  -DCMAKE_BUILD_TYPE=Release \
-  -DGGML_RPC=ON \
-  -DLLAMA_HIP_UMA=ON \
-  -DGGML_CUDA_ENABLE_UNIFIED_MEMORY=ON \
-  -DGGML_BMI2=ON \
-  -DGGML_FMA=ON \
-  -DGGML_F16C=ON \
-  -DGGML_CUDA_FA_ALL_QUANTS=ON \
-  -DLLAMA_BUILD_TESTS=OFF \
-  -DLLAMA_BUILD_EXAMPLES=OFF \
-  -DROCM_PATH=/opt/rocm \
-  -DHIP_PATH=/opt/rocm \
-  -DHIP_PLATFORM=amd \
-  && 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 7.2.2 repo
-RUN <<'EOF'
-tee /etc/yum.repos.d/rocm.repo <<REPO
-[ROCm-7.2.2]
-name=ROCm7.2.2
-baseurl=https://repo.radeon.com/rocm/rhel10/7.2.2/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 procps-ng \
-  && 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' \
-  > /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"]

toolboxes/Dockerfile.rocm-7.2.3

@@ -1,12 +1,12 @@
 # build stage
 FROM registry.fedoraproject.org/fedora:43 AS builder
 
-# rocm 7.2.2 repo
+# rocm 7.2.3 repo
 RUN <<'EOF'
 tee /etc/yum.repos.d/rocm.repo <<REPO
-[ROCm-7.2.2]
+[ROCm-7.2.3]
-name=ROCm7.2.2
+name=ROCm7.2.3
-baseurl=https://repo.radeon.com/rocm/rhel10/7.2.2/main
+baseurl=https://repo.radeon.com/rocm/rhel10/7.2.3/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -69,12 +69,12 @@ RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
 # runtime stage
 FROM registry.fedoraproject.org/fedora-minimal:43
 
-# rocm 7.2.2 repo
+# rocm 7.2.3 repo
 RUN <<'EOF'
 tee /etc/yum.repos.d/rocm.repo <<REPO
-[ROCm-7.2.2]
+[ROCm-7.2.3]
-name=ROCm7.2.2
+name=ROCm7.2.3
-baseurl=https://repo.radeon.com/rocm/rhel10/7.2.2/main
+baseurl=https://repo.radeon.com/rocm/rhel10/7.2.3/main
 enabled=1
 priority=50
 gpgcheck=1