Merge halo-box/llama.cpp master into strix (2026-09-15)

.ecrc

@@ -1,5 +1,5 @@
 {
-  "Exclude": ["^\\.gitmodules$", "stb_image\\.h"],
+  "Exclude": ["^\\.gitmodules$", "stb_image\\.h", "examples/test-cmake/build/", "examples/test-cmake/build-subdir/"],
   "Disable": {
     "IndentSize": true
   }

.github/actions/get-tag-name/action.yml

@@ -14,7 +14,7 @@ runs:
       run: |
         BUILD_NUMBER="$(git rev-list --count HEAD)"
         SHORT_HASH="$(git rev-parse --short=7 HEAD)"
-        if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
+        if [[ "${{ env.BRANCH_NAME }}" == "master" || "${{ env.BRANCH_NAME }}" == "b${BUILD_NUMBER}" ]]; then
           echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
         else
           SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')

.github/actions/windows-setup-cuda/action.yml

@@ -100,36 +100,36 @@ runs:
           echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
           echo "CUDA_PATH_V13_1=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
 
-    - name: Install Cuda Toolkit 13.3
-      if: ${{ inputs.cuda_version == '13.3' }}
+    - name: Install Cuda Toolkit 13.4 for x64
+      if: ${{ inputs.cuda_version == '13.4' && inputs.cuda_arch == 'x64' }}
       shell: pwsh
       run: |
-          mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
+          mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4"
           choco install unzip -y
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.3.33-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.3.29-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.3.33-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.3.33-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.5.1.27-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.3.33-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.3.29-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.3.27-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.3.27-archive.zip"
-          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.3.3.1-archive.zip"
-          unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_crt-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_cudart-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvcc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvrtc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libcublas-windows-x86_64-13.5.1.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libnvvm-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvtx-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_profiler_api-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\visual_studio_integration-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cccl-windows-x86_64-13.3.3.3.1-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
-          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
-          echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
-          echo "CUDA_PATH_V13_3=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.4.59-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.4.49-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.4.59-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.4.59-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.7.0.27-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.4.59-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.4.49-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.4.49-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.4.49-archive.zip"
+          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.4.2.1-archive.zip"
+          unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4"
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_crt-windows-x86_64-13.4.59-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_cudart-windows-x86_64-13.4.49-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_nvcc-windows-x86_64-13.4.59-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_nvrtc-windows-x86_64-13.4.59-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\libcublas-windows-x86_64-13.7.0.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\libnvvm-windows-x86_64-13.4.59-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_nvtx-windows-x86_64-13.4.49-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_profiler_api-windows-x86_64-13.4.49-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\visual_studio_integration-windows-x86_64-13.4.49-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cccl-windows-x86_64-13.3.4.2.1-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
+          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
+          echo "CUDA_PATH_V13_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
 
     - name: Install Cuda Toolkit 13.4 for ARM64
       if: ${{ inputs.cuda_version == '13.4' && inputs.cuda_arch == 'arm64' }}

.github/workflows/build-cpu.yml

@@ -222,7 +222,6 @@ jobs:
       #     7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
       #     $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
       #     cd build
-      #     $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
       #     & $sde -future -- ctest -L main -C Release --verbose --timeout 900
 
       - name: ccache-clear

.github/workflows/build-cuda-ubuntu.yml

@@ -179,7 +179,8 @@ jobs:
         id: cmake_build
         run: |
           cmake -B build -S . \
-            -DGGML_MUSA=ON
+            -DGGML_MUSA=ON \
+            -DMUSA_ARCHITECTURES=21
           time cmake --build build --config Release -j $(nproc)
 
       - name: ccache-buckets-save

.github/workflows/build-cuda-windows.yml

@@ -34,7 +34,7 @@ jobs:
           - cuda: '12.4'
             arch: x64
             defines: '-DGGML_CUDA_CUB_3DOT2=ON'
-          - cuda: '13.3'
+          - cuda: '13.4'
             arch: x64
             defines: ''
           - cuda: '13.4'

.github/workflows/build-ibm.yml

@@ -35,10 +35,15 @@ env:
   LLAMA_ARG_LOG_TIMESTAMPS: 1
 
 jobs:
-
   ubuntu-24-s390x:
+    name: ubuntu-24-s390x (VXE ${{ matrix.vxe }})
     runs-on: ubuntu-24.04-s390x
 
+    strategy:
+      fail-fast: false
+      matrix:
+        vxe: ["ON", "OFF"]  # `-DGGML_VXE=ON/OFF`
+
     steps:
       - name: Clone
         id: checkout
@@ -78,7 +83,8 @@ jobs:
         run: |
           cmake -B build \
             -DLLAMA_FATAL_WARNINGS=ON \
-            -DGGML_RPC=ON
+            -DGGML_RPC=ON \
+            -DGGML_VXE=${{ matrix.vxe }}
           time cmake --build build --config Release -j $(nproc)
 
       - name: Test

.github/workflows/build-self-hosted.yml

@@ -7,6 +7,7 @@ on:
       - master
     paths: [
       '.github/workflows/build-self-hosted.yml',
+      'ci/run.sh',
       '**/CMakeLists.txt',
       '**/.cmake',
       '**/*.h',
@@ -28,6 +29,7 @@ on:
     types: [opened, synchronize, reopened]
     paths: [
       '.github/workflows/build-self-hosted.yml',
+      'ci/run.sh',
       '**/CMakeLists.txt',
       '**/.cmake',
       '**/*.h',
@@ -161,10 +163,10 @@ jobs:
       - name: Dawn Dependency
         id: dawn-depends
         run: |
-          DAWN_VERSION="v20260317.182325"
+          DAWN_VERSION="v20260908.214631"
           DAWN_OWNER="google"
           DAWN_REPO="dawn"
-          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
+          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-ubuntu-latest-Release"
           echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
           curl -L -o artifact.tar.gz \
             "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
@@ -247,10 +249,10 @@ jobs:
       - name: Dawn Dependency
         id: dawn-depends
         run: |
-          DAWN_VERSION="v20260317.182325"
+          DAWN_VERSION="v20260908.214631"
           DAWN_OWNER="google"
           DAWN_REPO="dawn"
-          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
+          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-macos-latest-Release"
           echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
           curl -L -o artifact.tar.gz \
             "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
@@ -360,7 +362,7 @@ jobs:
           LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
 
   cpu-arm64-high-perf-graviton4:
-    runs-on: ah-ubuntu_22_04-c8g_8x
+    runs-on: ah-ubuntu_24_04-c8g_8x
 
     steps:
       - name: Clone
@@ -403,7 +405,7 @@ jobs:
           bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
 
   cpu-arm64-graviton4-kleidiai:
-    runs-on: ah-ubuntu_22_04-c8g_8x
+    runs-on: ah-ubuntu_24_04-c8g_8x
 
     steps:
       - name: Clone

.github/workflows/build-wasm.yml

@@ -69,7 +69,7 @@ jobs:
 
       - name: Fetch emdawnwebgpu
         run: |
-          DAWN_TAG="v20260317.182325"
+          DAWN_TAG="v20260908.214631"
           EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip"
           echo "Downloading ${EMDAWN_PKG}"
           curl -L -o emdawn.zip \

.github/workflows/build-webgpu.yml

@@ -78,10 +78,10 @@ jobs:
       - name: Dawn Dependency
         id: dawn-depends
         run: |
-          DAWN_VERSION="v20260317.182325"
+          DAWN_VERSION="v20260908.214631"
           DAWN_OWNER="google"
           DAWN_REPO="dawn"
-          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
+          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-macos-latest-Release"
           echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
           curl -L -o artifact.tar.gz \
             "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
@@ -148,10 +148,10 @@ jobs:
         id: dawn-depends
         run: |
           sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
-          DAWN_VERSION="v20260317.182325"
+          DAWN_VERSION="v20260908.214631"
           DAWN_OWNER="google"
           DAWN_REPO="dawn"
-          DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
+          DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-ubuntu-latest-Release"
           echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
           curl -L -o artifact.tar.gz \
             "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"

.github/workflows/code-style.yml

@@ -15,7 +15,7 @@ concurrency:
 
 jobs:
   model-naming:
-    runs-on: [self-hosted, fast]
+    runs-on: ubuntu-slim
     steps:
       - uses: actions/checkout@v6
       - name: Check model naming conventions

.github/workflows/editorconfig.yml

@@ -15,7 +15,7 @@ concurrency:
 
 jobs:
   editorconfig:
-    runs-on: [self-hosted, fast]
+    runs-on: ubuntu-slim
     steps:
       - uses: actions/checkout@v6
       - uses: editorconfig-checker/action-editorconfig-checker@840e866d93b8e032123c23bac69dece044d4d84c # v2.2.0

.github/workflows/fusion.yml

@@ -9,7 +9,9 @@ on:
       '.github/workflows/fusion.yml',
       'ggml/**',
       'tests/fusion/**',
-      'tests/test-fusion.cpp'
+      'tests/test-fusion.cpp',
+      'tests/test-llama-archs.cpp',
+      'src/models/**'
     ]
 
   pull_request:
@@ -18,7 +20,9 @@ on:
       '.github/workflows/fusion.yml',
       'ggml/**',
       'tests/fusion/**',
-      'tests/test-fusion.cpp'
+      'tests/test-fusion.cpp',
+      'tests/test-llama-archs.cpp',
+      'src/models/**'
     ]
 
 concurrency: