diff --git a/.github/workflows/build-3rd-party.yml b/.github/workflows/build-3rd-party.yml
new file mode 100644
index 0000000000..642d978644
--- /dev/null
+++ b/.github/workflows/build-3rd-party.yml
@@ -0,0 +1,57 @@
+name: CI (3rd-party)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-3rd-party.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  ubuntu-24-llguidance:
+    runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential libssl-dev
+
+      - name: Build
+        id: cmake_build
+        run: |
+          cmake -B build \
+            -DLLAMA_FATAL_WARNINGS=ON \
+            -DLLAMA_LLGUIDANCE=ON
+          cmake --build build --config Release -j $(nproc)
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          ctest -L main --verbose --timeout 900
+
diff --git a/.github/workflows/build-android.yml b/.github/workflows/build-android.yml
new file mode 100644
index 0000000000..cd9d99ffab
--- /dev/null
+++ b/.github/workflows/build-android.yml
@@ -0,0 +1,140 @@
+name: CI (android)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-android.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp'
+    ]
+
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: [
+      '.github/workflows/build-android.yml',
+      'examples/llama.android/**'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  android:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+
+      # Disabled due to size (400MB) and always 0 cache hits
+      # - name: ccache
+      #   uses: ggml-org/ccache-action@v1.2.16
+      #   with:
+      #     key: android-build
+      #     evict-old-files: 1d
+
+      - name: Set up JDK
+        uses: actions/setup-java@v5
+        with:
+          java-version: 17
+          distribution: zulu
+
+      - name: Setup Android SDK
+        uses: android-actions/setup-android@v3
+        with:
+          log-accepted-android-sdk-licenses: false
+
+      - name: Build
+        run: |
+          cd examples/llama.android
+          ./gradlew build --no-daemon
+
+  android-ndk:
+    runs-on: ubuntu-latest
+
+    env:
+      OPENCL_VERSION: 2025.07.22
+
+    strategy:
+      matrix:
+        include:
+          - build: 'arm64-cpu'
+            defines: '-D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=OFF -D GGML_OPENMP=OFF'
+          - build: 'arm64-snapdragon'
+            defines: '--preset arm64-android-snapdragon-release'
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Install OpenCL Headers and Libs
+        id: install_opencl
+        if: ${{ matrix.build == 'arm64-snapdragon' }}
+        run: |
+          mkdir opencl
+          curl -L -o opencl/clhpp.tar.gz      https://github.com/KhronosGroup/OpenCL-CLHPP/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+          curl -L -o opencl/headers.tar.gz    https://github.com/KhronosGroup/OpenCL-Headers/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+          curl -L -o opencl/icd-loader.tar.gz https://github.com/KhronosGroup/OpenCL-ICD-Loader/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
+          tar -xaf opencl/headers.tar.gz    -C opencl
+          tar -xaf opencl/clhpp.tar.gz      -C opencl
+          tar -xaf opencl/icd-loader.tar.gz -C opencl
+          sudo cp -r opencl/OpenCL-Headers-${OPENCL_VERSION}/CL         ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include
+          sudo cp -r opencl/OpenCL-CLHPP-${OPENCL_VERSION}/include/CL/* ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include/CL
+          cd opencl/OpenCL-ICD-Loader-${OPENCL_VERSION}
+          cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -DOPENCL_ICD_LOADER_HEADERS_DIR=${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=31 -DANDROID_STL=c++_shared
+          cmake --build build
+          sudo cp build/libOpenCL.so ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android
+          rm -rf opencl
+
+      - name: Install Hexagon SDK
+        id: install_hexsdk
+        if: ${{ matrix.build == 'arm64-snapdragon' }}
+        env:
+          HEXSDK_VER: 6.4.0.2
+          HEXTLS_VER: 19.0.04
+        run: |
+          curl -L -o hex-sdk.tar.gz https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v$HEXSDK_VER/hexagon-sdk-v$HEXSDK_VER-amd64-lnx.tar.xz
+          mkdir hex-sdk
+          tar -xaf hex-sdk.tar.gz -C hex-sdk
+          ls -l hex-sdk
+          sudo mv hex-sdk /opt/hexagon
+          echo "HEXAGON_SDK_ROOT=/opt/hexagon/$HEXSDK_VER"                                     >> "$GITHUB_ENV"
+          echo "HEXAGON_TOOLS_ROOT=/opt/hexagon/$HEXSDK_VER/tools/HEXAGON_Tools/$HEXTLS_VER"   >> "$GITHUB_ENV"
+          echo "DEFAULT_HLOS_ARCH=64"                                                          >> "$GITHUB_ENV"
+          echo "DEFAULT_TOOLS_VARIANT=toolv19"                                                 >> "$GITHUB_ENV"
+          echo "DEFAULT_NO_QURT_INC=0"                                                         >> "$GITHUB_ENV"
+          echo "DEFAULT_DSP_ARCH=v73"                                                          >> "$GITHUB_ENV"
+
+      - name: Update CMake presets
+        id: update_presets
+        if: ${{ matrix.build == 'arm64-snapdragon' }}
+        run: |
+          cp docs/backend/snapdragon/CMakeUserPresets.json .
+
+      - name: Build
+        id: ndk_build
+        run: |
+          cmake ${{ matrix.defines }} -B build
+          cmake --build build
+          cmake --install build --prefix pkg-adb/llama.cpp
+
+      - name: Test
+        id: cmake_test
+        run: |
+          echo "FIXME: test on devices"
diff --git a/.github/workflows/build-apple.yml b/.github/workflows/build-apple.yml
new file mode 100644
index 0000000000..51f0ef2302
--- /dev/null
+++ b/.github/workflows/build-apple.yml
@@ -0,0 +1,214 @@
+name: CI (apple)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-apple.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.swift',
+      '**/*.m',
+      '**/*.metal'
+    ]
+
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: [
+      '.github/workflows/build-apple.yml',
+      'ggml/src/ggml-metal/**'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  macOS-latest-ios:
+    runs-on: macos-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.16
+        with:
+          key: macOS-latest-ios
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Build
+        id: cmake_build
+        run: |
+          sysctl -a
+          cmake -B build -G Xcode \
+            -DGGML_METAL_USE_BF16=ON \
+            -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_BUILD_COMMON=OFF \
+            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DLLAMA_BUILD_SERVER=OFF \
+            -DCMAKE_SYSTEM_NAME=iOS \
+            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
+            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
+          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+
+  macos-latest-ios-xcode:
+    runs-on: macos-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v6
+
+      - name: Setup Xcode
+        uses: ggml-org/setup-xcode@v1
+        with:
+          xcode-version: latest-stable
+
+      - name: Build
+        id: cmake_build
+        run: |
+          sysctl -a
+          cmake -B build -G Xcode \
+            -DGGML_METAL_USE_BF16=ON \
+            -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_OPENSSL=OFF \
+            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DLLAMA_BUILD_SERVER=OFF \
+            -DCMAKE_SYSTEM_NAME=iOS \
+            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
+            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
+          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+
+      - name: xcodebuild for swift package
+        id: xcodebuild
+        run: |
+          ./build-xcframework.sh
+
+      - name: Upload xcframework artifact
+        uses: actions/upload-artifact@v6
+        with:
+          name: llama-xcframework
+          path: build-apple/llama.xcframework/
+          retention-days: 1
+
+      - name: Build Xcode project
+        run: |
+          xcodebuild -downloadPlatform iOS
+          xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
+
+  macOS-latest-tvos:
+    runs-on: macos-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.16
+        with:
+          key: macOS-latest-tvos
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Build
+        id: cmake_build
+        run: |
+          sysctl -a
+          cmake -B build -G Xcode \
+            -DGGML_METAL_USE_BF16=ON \
+            -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_BUILD_COMMON=OFF \
+            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DLLAMA_BUILD_SERVER=OFF \
+            -DCMAKE_SYSTEM_NAME=tvOS \
+            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
+            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
+          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+
+  macOS-latest-visionos:
+    runs-on: macos-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Build
+        id: cmake_build
+        run: |
+          sysctl -a
+          cmake -B build -G Xcode \
+            -DGGML_METAL_USE_BF16=ON \
+            -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_BUILD_COMMON=OFF \
+            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DLLAMA_BUILD_SERVER=OFF \
+            -DCMAKE_SYSTEM_NAME=visionOS \
+            -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
+            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
+          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+
+  macOS-latest-swift:
+    runs-on: macos-latest
+    needs: macos-latest-ios-xcode
+
+    strategy:
+      matrix:
+        destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.16
+        with:
+          key: macOS-latest-swift
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Download xcframework artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: llama-xcframework
+          path: build-apple/llama.xcframework/
+
+      - name: Build llama.cpp with CMake
+        id: cmake_build
+        run: |
+          sysctl -a
+          cmake -B build -G Xcode \
+            -DGGML_METAL_USE_BF16=ON \
+            -DGGML_METAL_EMBED_LIBRARY=ON \
+            -DLLAMA_OPENSSL=OFF \
+            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DLLAMA_BUILD_SERVER=OFF \
+            -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
+          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
diff --git a/.github/workflows/build-cache.yml b/.github/workflows/build-cache.yml
index dffbf2b4ab..bc0a92c7fc 100644
--- a/.github/workflows/build-cache.yml
+++ b/.github/workflows/build-cache.yml
@@ -37,31 +37,31 @@ jobs:
           path: ./vulkan_sdk
           version: ${{ env.VULKAN_SDK_VERSION }}
 
-  ubuntu-24-spacemit-cache:
-    runs-on: ubuntu-24.04
+  #ubuntu-24-spacemit-cache:
+  #  runs-on: ubuntu-24.04
 
-    env:
-      # Make sure this is in sync with build-linux-cross.yml
-      SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
+  #  env:
+  #    # Make sure this is in sync with build-linux-cross.yml
+  #    SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
 
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
+  #  steps:
+  #    - name: Clone
+  #      id: checkout
+  #      uses: actions/checkout@v6
 
-      - name: Setup Cache
-        uses: actions/cache@v5
-        id: cache-toolchain
-        with:
-          path: ./spacemit_toolchain
-          key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
+  #    - name: Setup Cache
+  #      uses: actions/cache@v5
+  #      id: cache-toolchain
+  #      with:
+  #        path: ./spacemit_toolchain
+  #        key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
 
-      - name: Setup SpacemiT Toolchain
-        if: steps.cache-toolchain.outputs.cache-hit != 'true'
-        uses: ./.github/actions/linux-setup-spacemit
-        with:
-          path: ./spacemit_toolchain
-          version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
+  #    - name: Setup SpacemiT Toolchain
+  #      if: steps.cache-toolchain.outputs.cache-hit != 'true'
+  #      uses: ./.github/actions/linux-setup-spacemit
+  #      with:
+  #        path: ./spacemit_toolchain
+  #        version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
 
   ubuntu-24-openvino-cache:
     runs-on: ubuntu-24.04
diff --git a/.github/workflows/build-cann.yml b/.github/workflows/build-cann.yml
new file mode 100644
index 0000000000..de641ca148
--- /dev/null
+++ b/.github/workflows/build-cann.yml
@@ -0,0 +1,102 @@
+name: CI (cann)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-cann.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp'
+    ]
+
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: [
+      '.github/workflows/build-cann.yml',
+      'ggml/src/ggml-cann/**'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  openEuler-latest-cann:
+    defaults:
+      run:
+        shell: bash -el {0}
+    strategy:
+      matrix:
+        arch: [x86, aarch64]
+        chip_type: ['910b', '310p']
+        build: ['Release']
+        use_acl_graph: ['on', 'off']
+        exclude:
+          # 310P does not support USE_ACL_GRAPH=on
+          - chip_type: '310p'
+            use_acl_graph: 'on'
+    runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Free up disk space
+        uses: ggml-org/free-disk-space@v1.3.1
+        with:
+          tool-cache: true
+
+      - name: Set container image
+        id: cann-image
+        run: |
+          image="ascendai/cann:${{ matrix.chip_type == '910b' &&  '8.3.rc2-910b-openeuler24.03-py3.11' || '8.3.rc2-310p-openeuler24.03-py3.11' }}"
+          echo "image=${image}" >> "${GITHUB_OUTPUT}"
+
+      - name: Pull container image
+        run: docker pull "${{ steps.cann-image.outputs.image }}"
+
+      - name: Build
+        env:
+          BUILD_TYPE: ${{ matrix.build }}
+          SOC_TYPE: ascend${{ matrix.chip_type }}
+          USE_ACL_GRAPH: ${{ matrix.use_acl_graph }}
+        run: |
+          HOST_UID=$(id -u)
+          HOST_GID=$(id -g)
+
+          docker run --rm \
+            -v "${PWD}:/workspace" \
+            -w /workspace \
+            -e SOC_TYPE=${SOC_TYPE} \
+            -e BUILD_TYPE=${BUILD_TYPE} \
+            -e USE_ACL_GRAPH=${USE_ACL_GRAPH} \
+            "${{ steps.cann-image.outputs.image }}" \
+            bash -lc '
+              set -e
+              yum install -y --setopt=install_weak_deps=False --setopt=tsflags=nodocs git gcc gcc-c++ make cmake openssl-devel
+              yum clean all && rm -rf /var/cache/yum
+              git config --global --add safe.directory "/workspace"
+              export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH}
+              cmake -S . -B build \
+                  -DCMAKE_BUILD_TYPE=${BUILD_TYPE} \
+                  -DGGML_CANN=on \
+                  -DSOC_TYPE=${SOC_TYPE} \
+                  -DUSE_ACL_GRAPH=${USE_ACL_GRAPH}
+              cmake --build build -j $(nproc)
+
+              chown -R '"${HOST_UID}"':'"${HOST_GID}"' /workspace/build
+            '
diff --git a/.github/workflows/build-linux-cross.yml b/.github/workflows/build-cross.yml
similarity index 93%
rename from .github/workflows/build-linux-cross.yml
rename to .github/workflows/build-cross.yml
index dbcc1ee2ae..74508129ac 100644
--- a/.github/workflows/build-linux-cross.yml
+++ b/.github/workflows/build-cross.yml
@@ -1,7 +1,24 @@
-name: Build on Linux using cross-compiler
+name: CI (cross)
 on:
+  # only manual triggers due to low-importance of the workflows
+  # TODO: for regular runs, provision dedicated self-hosted runners
   workflow_dispatch:
-  workflow_call:
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-cross.yml',
+      'ggml/src/spacemit/*',
+      'ggml/src/arch/loongarch/*'
+    ]
+  # run once every week
+  schedule:
+    - cron: '0 0 * * 0'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
 
 jobs:
   # ubuntu-24-riscv64-cpu-cross:
@@ -264,15 +281,15 @@ jobs:
     steps:
       - uses: actions/checkout@v6
 
-      - name: Use SpacemiT Toolchain Cache
-        uses: actions/cache@v5
-        id: cache-toolchain
-        with:
-          path: ./spacemit_toolchain
-          key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
+      #- name: Use SpacemiT Toolchain Cache
+      #  uses: actions/cache@v5
+      #  id: cache-toolchain
+      #  with:
+      #    path: ./spacemit_toolchain
+      #    key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
 
       - name: Setup SpacemiT Toolchain
-        if: steps.cache-toolchain.outputs.cache-hit != 'true'
+        #if: steps.cache-toolchain.outputs.cache-hit != 'true'
         uses: ./.github/actions/linux-setup-spacemit
         with:
           path: ./spacemit_toolchain
diff --git a/.github/workflows/build-msys.yml b/.github/workflows/build-msys.yml
new file mode 100644
index 0000000000..431d9b6a53
--- /dev/null
+++ b/.github/workflows/build-msys.yml
@@ -0,0 +1,72 @@
+name: CI (msys)
+
+on:
+  # only manual triggers due to low-importance of the workflows
+  # TODO: for regular runs, provision dedicated self-hosted runners
+  workflow_dispatch:
+  # run once every week
+  schedule:
+    - cron: '0 0 * * 0'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  windows-msys2:
+    runs-on: windows-2025
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - { sys: UCRT64,  env: ucrt-x86_64,  build: Release }
+          - { sys: CLANG64, env: clang-x86_64, build: Release }
+
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+
+      #- name: ccache
+      #  uses: ggml-org/ccache-action@v1.2.16
+      #  with:
+      #    key: windows-msys2
+      #    variant: ccache
+      #    evict-old-files: 1d
+      #    save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Setup ${{ matrix.sys }}
+        uses: msys2/setup-msys2@v2
+        with:
+          update: true
+          msystem: ${{matrix.sys}}
+          install: >-
+            base-devel
+            git
+            mingw-w64-${{matrix.env}}-toolchain
+            mingw-w64-${{matrix.env}}-cmake
+            mingw-w64-${{matrix.env}}-openblas
+
+      - name: Build using CMake
+        shell: msys2 {0}
+        run: |
+            cmake -B build
+            cmake --build build --config ${{ matrix.build }} -j $(nproc)
+
+      - name: Clean after building using CMake
+        shell: msys2 {0}
+        run: |
+            rm -rf build
+
+      - name: Build using CMake w/ OpenBLAS
+        shell: msys2 {0}
+        run: |
+            cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+            cmake --build build --config ${{ matrix.build }} -j $(nproc)
diff --git a/.github/workflows/build-riscv.yml b/.github/workflows/build-riscv.yml
new file mode 100644
index 0000000000..36a3a1155a
--- /dev/null
+++ b/.github/workflows/build-riscv.yml
@@ -0,0 +1,136 @@
+name: CI (riscv)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-riscv.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp'
+    ]
+
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: [
+      '.github/workflows/build-riscv.yml',
+      'ggml/src/ggml-cpu/arch/riscv/**'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  ubuntu-riscv64-native-sanitizer:
+    runs-on: RISCV64
+
+    continue-on-error: true
+
+    strategy:
+      matrix:
+        sanitizer: [ADDRESS, THREAD, UNDEFINED]
+        build_type: [Debug]
+
+    steps:
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+
+          # Install necessary packages
+          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
+
+          # Set gcc-14 and g++-14 as the default compilers
+          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
+
+          # Install Rust stable version
+          rustup install stable
+          rustup default stable
+
+          git lfs install
+
+      - name: GCC version check
+        run: |
+          gcc --version
+          g++ --version
+
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Setup ccache
+        run: |
+          # Unique cache directory per matrix combination
+          export CCACHE_DIR="$HOME/.ccache/sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}"
+          mkdir -p "$CCACHE_DIR"
+
+          # Configure ccache
+          ccache --set-config=max_size=5G
+          ccache --set-config=compression=true
+          ccache --set-config=compression_level=6
+          ccache --set-config=cache_dir="$CCACHE_DIR"
+          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+          ccache --set-config=hash_dir=false
+
+          # Export for subsequent steps
+          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
+
+      - name: Build
+        id: cmake_build
+        if: ${{ matrix.sanitizer != 'THREAD' }}
+        run: |
+          cmake -B build \
+            -DLLAMA_OPENSSL=OFF \
+            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
+            -DGGML_OPENMP=ON \
+            -DLLAMA_BUILD_EXAMPLES=ON \
+            -DLLAMA_BUILD_TOOLS=ON \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+      - name: Build (no OpenMP)
+        id: cmake_build_no_openmp
+        if: ${{ matrix.sanitizer == 'THREAD' }}
+        run: |
+          cmake -B build \
+            -DLLAMA_OPENSSL=OFF \
+            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
+            -DGGML_OPENMP=OFF \
+            -DLLAMA_BUILD_EXAMPLES=ON \
+            -DLLAMA_BUILD_TOOLS=ON \
+            -DLLAMA_BUILD_TESTS=OFF \
+            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          ctest -L main --verbose --timeout 900
diff --git a/.github/workflows/build-sanitize.yml b/.github/workflows/build-sanitize.yml
new file mode 100644
index 0000000000..0b17857504
--- /dev/null
+++ b/.github/workflows/build-sanitize.yml
@@ -0,0 +1,87 @@
+name: CI (sanitize)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-sanitize.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  ubuntu-latest-sanitizer:
+    runs-on: ubuntu-latest
+
+    continue-on-error: true
+
+    strategy:
+      matrix:
+        sanitizer: [ADDRESS, THREAD, UNDEFINED]
+        build_type: [Debug]
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.16
+        with:
+          key: ubuntu-latest-sanitizer-${{ matrix.sanitizer }}
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential libssl-dev
+
+      - name: Build
+        id: cmake_build
+        if: ${{ matrix.sanitizer != 'THREAD' }}
+        run: |
+          cmake -B build \
+            -DLLAMA_FATAL_WARNINGS=ON \
+            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
+
+          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+      - name: Build (no OpenMP)
+        id: cmake_build_no_openmp
+        if: ${{ matrix.sanitizer == 'THREAD' }}
+        run: |
+          cmake -B build \
+            -DLLAMA_FATAL_WARNINGS=ON \
+            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
+            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
+            -DGGML_OPENMP=OFF
+
+          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          ctest -L main --verbose --timeout 900
diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.yml
index eba06b96bc..7c7710fe45 100644
--- a/.github/workflows/build-self-hosted.yml
+++ b/.github/workflows/build-self-hosted.yml
@@ -222,15 +222,7 @@ jobs:
         id: checkout
         uses: actions/checkout@v6
 
-      - name: Use OpenVINO Toolkit Cache
-        uses: actions/cache@v5
-        id: cache-openvino
-        with:
-          path: ./openvino_toolkit
-          key: openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
-
       - name: Setup OpenVINO Toolkit
-        if: steps.cache-openvino.outputs.cache-hit != 'true'
         uses: ./.github/actions/linux-setup-openvino
         with:
           path: ./openvino_toolkit
diff --git a/.github/workflows/build-vulkan.yml b/.github/workflows/build-vulkan.yml
new file mode 100644
index 0000000000..b25ec51471
--- /dev/null
+++ b/.github/workflows/build-vulkan.yml
@@ -0,0 +1,96 @@
+name: CI (vulkan)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-vulkan.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.comp',
+      '**/*.glsl'
+    ]
+
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: [
+      '.github/workflows/build-vulkan.yml',
+      'ggml/src/ggml-vulkan/**'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  GGML_NLOOP: 3
+  GGML_N_THREADS: 1
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+  ubuntu-24-vulkan-llvmpipe:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.16
+        with:
+          key: ubuntu-24-vulkan-llvmpipe
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo add-apt-repository -y ppa:kisak/kisak-mesa
+          sudo apt-get update -y
+          sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
+
+      - name: Get latest Vulkan SDK version
+        id: vulkan_sdk_version
+        run: |
+          echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
+
+      - name: Use Vulkan SDK Cache
+        uses: actions/cache@v5
+        id: cache-sdk
+        with:
+          path: ./vulkan_sdk
+          key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
+
+      - name: Setup Vulkan SDK
+        if: steps.cache-sdk.outputs.cache-hit != 'true'
+        uses: ./.github/actions/linux-setup-vulkan-llvmpipe
+        with:
+          path: ./vulkan_sdk
+          version: ${{ env.VULKAN_SDK_VERSION }}
+
+      - name: Build
+        id: cmake_build
+        run: |
+          source ./vulkan_sdk/setup-env.sh
+          cmake -B build \
+            -DGGML_VULKAN=ON
+          cmake --build build --config Release -j $(nproc)
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          export GGML_VK_VISIBLE_DEVICES=0
+          export GGML_VK_DISABLE_F16=1
+          export GGML_VK_DISABLE_COOPMAT=1
+          # This is using llvmpipe and runs slower than other backends
+          ctest -L main --verbose --timeout 4800
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 460a770122..fef08d4c00 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -7,7 +7,6 @@ on:
       - master
     paths: [
       '.github/workflows/build.yml',
-      '.github/workflows/build-linux-cross.yml',
       '.github/workflows/build-cmake-pkg.yml',
       '**/CMakeLists.txt',
       '**/.cmake',
@@ -29,7 +28,6 @@ on:
     types: [opened, synchronize, reopened]
     paths: [
       '.github/workflows/build.yml',
-      '.github/workflows/build-linux-cross.yml',
       '.github/workflows/build-cmake-pkg.yml',
       '**/CMakeLists.txt',
       '**/.cmake',
@@ -59,7 +57,10 @@ env:
   LLAMA_LOG_TIMESTAMPS: 1
 
 jobs:
-  macOS-latest-cmake-arm64:
+  build-cmake-pkg:
+    uses: ./.github/workflows/build-cmake-pkg.yml
+
+  macOS-latest-arm64:
     runs-on: macos-latest
 
     steps:
@@ -70,7 +71,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: macOS-latest-cmake-arm64
+          key: macOS-latest-arm64
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -95,7 +96,7 @@ jobs:
           cd build
           ctest -L main -E "test-llama-archs" --verbose --timeout 900
 
-  macOS-latest-cmake-x64:
+  macOS-latest-x64:
     runs-on: macos-15-intel
 
     steps:
@@ -106,7 +107,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: macOS-latest-cmake-x64
+          key: macOS-latest-x64
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -131,7 +132,7 @@ jobs:
           cd build
           ctest -L main --verbose --timeout 900
 
-  macOS-latest-cmake-arm64-webgpu:
+  macOS-latest-arm64-webgpu:
     runs-on: macos-latest
 
     steps:
@@ -142,7 +143,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: macOS-latest-cmake-arm64-webgpu
+          key: macOS-latest-arm64-webgpu
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -173,7 +174,7 @@ jobs:
           cd build
           ctest -L main --verbose --timeout 900
 
-  ubuntu-cpu-cmake:
+  ubuntu-cpu:
     strategy:
       matrix:
         include:
@@ -196,7 +197,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-cpu-cmake-${{ matrix.build }}
+          key: ubuntu-cpu-${{ matrix.build }}
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -258,98 +259,11 @@ jobs:
           wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
           ./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
-  ubuntu-latest-cmake-sanitizer:
+  ubuntu-latest-rpc:
     runs-on: ubuntu-latest
 
     continue-on-error: true
 
-    strategy:
-      matrix:
-        sanitizer: [ADDRESS, THREAD, UNDEFINED]
-        build_type: [Debug]
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }}
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Dependencies
-        id: depends
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential libssl-dev
-
-      - name: Build
-        id: cmake_build
-        if: ${{ matrix.sanitizer != 'THREAD' }}
-        run: |
-          cmake -B build \
-            -DLLAMA_FATAL_WARNINGS=ON \
-            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
-
-          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
-
-      - name: Build (no OpenMP)
-        id: cmake_build_no_openmp
-        if: ${{ matrix.sanitizer == 'THREAD' }}
-        run: |
-          cmake -B build \
-            -DLLAMA_FATAL_WARNINGS=ON \
-            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DGGML_OPENMP=OFF
-
-          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose --timeout 900
-
-  ubuntu-24-llguidance:
-    runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Dependencies
-        id: depends
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential libssl-dev
-
-      - name: Build
-        id: cmake_build
-        run: |
-          cmake -B build \
-            -DLLAMA_FATAL_WARNINGS=ON \
-            -DLLAMA_LLGUIDANCE=ON
-          cmake --build build --config Release -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose --timeout 900
-
-  ubuntu-24-cmake-rpc:
-    runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
-
-    continue-on-error: true
-
     steps:
       - name: Clone
         id: checkout
@@ -374,7 +288,7 @@ jobs:
           cd build
           ctest -L main --verbose
 
-  ubuntu-24-cmake-vulkan-deb:
+  ubuntu-24-vulkan:
     runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
 
     steps:
@@ -401,7 +315,7 @@ jobs:
         run: |
           cmake --build build -j $(nproc)
 
-  ubuntu-24-cmake-vulkan:
+  ubuntu-24-webgpu:
     runs-on: ubuntu-24.04
 
     steps:
@@ -412,66 +326,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-24-cmake-vulkan
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Dependencies
-        id: depends
-        run: |
-          sudo add-apt-repository -y ppa:kisak/kisak-mesa
-          sudo apt-get update -y
-          sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
-
-      - name: Get latest Vulkan SDK version
-        id: vulkan_sdk_version
-        run: |
-          echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
-
-      - name: Use Vulkan SDK Cache
-        uses: actions/cache@v5
-        id: cache-sdk
-        with:
-          path: ./vulkan_sdk
-          key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
-
-      - name: Setup Vulkan SDK
-        if: steps.cache-sdk.outputs.cache-hit != 'true'
-        uses: ./.github/actions/linux-setup-vulkan
-        with:
-          path: ./vulkan_sdk
-          version: ${{ env.VULKAN_SDK_VERSION }}
-
-      - name: Build
-        id: cmake_build
-        run: |
-          source ./vulkan_sdk/setup-env.sh
-          cmake -B build \
-            -DGGML_VULKAN=ON
-          cmake --build build --config Release -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          export GGML_VK_VISIBLE_DEVICES=0
-          export GGML_VK_DISABLE_F16=1
-          export GGML_VK_DISABLE_COOPMAT=1
-          # This is using llvmpipe and runs slower than other backends
-          ctest -L main --verbose --timeout 4800
-
-  ubuntu-24-cmake-webgpu:
-    runs-on: ubuntu-24.04
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: ubuntu-24-cmake-webgpu
+          key: ubuntu-24-webgpu
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -531,7 +386,7 @@ jobs:
           # This is using llvmpipe and runs slower than other backends
           ctest -L main --verbose --timeout 900
 
-  ubuntu-24-wasm-webgpu:
+  ubuntu-24-webgpu-wasm:
     runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
 
     steps:
@@ -565,7 +420,7 @@ jobs:
 
           cmake --build build-wasm --target test-backend-ops -j $(nproc)
 
-  ubuntu-22-cmake-hip:
+  ubuntu-22-hip:
     runs-on: ubuntu-22.04
     container: rocm/dev-ubuntu-22.04:6.1.2
 
@@ -583,7 +438,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-22-cmake-hip
+          key: ubuntu-22-hip
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -596,7 +451,7 @@ jobs:
             -DGGML_HIP=ON
           cmake --build build --config Release -j $(nproc)
 
-  ubuntu-22-cmake-musa:
+  ubuntu-22-musa:
     runs-on: ubuntu-22.04
     container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
 
@@ -614,7 +469,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-22-cmake-musa
+          key: ubuntu-22-musa
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -625,7 +480,7 @@ jobs:
             -DGGML_MUSA=ON
           cmake --build build --config Release -j $(nproc)
 
-  ubuntu-22-cmake-sycl:
+  ubuntu-22-sycl:
     runs-on: ubuntu-22.04
 
     continue-on-error: true
@@ -660,7 +515,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-22-cmake-sycl
+          key: ubuntu-22-sycl
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -674,7 +529,7 @@ jobs:
             -DCMAKE_CXX_COMPILER=icpx
           cmake --build build --config Release -j $(nproc)
 
-  ubuntu-22-cmake-sycl-fp16:
+  ubuntu-22-sycl-fp16:
     runs-on: ubuntu-22.04
 
     continue-on-error: true
@@ -709,7 +564,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-22-cmake-sycl-fp16
+          key: ubuntu-22-sycl-fp16
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -724,8 +579,8 @@ jobs:
             -DGGML_SYCL_F16=ON
           cmake --build build --config Release -j $(nproc)
 
-  ubuntu-24-cmake-openvino:
-      name: ubuntu-24-cmake-openvino-${{ matrix.openvino_device }}
+  ubuntu-24-openvino:
+      name: ubuntu-24-openvino-${{ matrix.openvino_device }}
       strategy:
         matrix:
           include:
@@ -749,10 +604,12 @@ jobs:
           uses: actions/checkout@v6
 
         - name: ccache
+          if: runner.environment == 'github-hosted'
           uses: ggml-org/ccache-action@v1.2.16
           with:
-            key: ubuntu-24-cmake-openvino-${{ matrix.variant }}-no-preset-v1
+            key: ubuntu-24-openvino-${{ matrix.variant }}-no-preset-v1
             evict-old-files: 1d
+            save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
         - name: Dependencies
           id: depends
@@ -762,6 +619,7 @@ jobs:
             sudo apt-get install -y ocl-icd-opencl-dev opencl-headers opencl-clhpp-headers intel-opencl-icd
 
         - name: Use OpenVINO Toolkit Cache
+          if: runner.environment == 'github-hosted'
           uses: actions/cache@v5
           id: cache-openvino
           with:
@@ -801,194 +659,7 @@ jobs:
             fi
             ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
 
-  build-linux-cross:
-    uses: ./.github/workflows/build-linux-cross.yml
-
-  build-cmake-pkg:
-    uses: ./.github/workflows/build-cmake-pkg.yml
-
-  macOS-latest-cmake-ios:
-    runs-on: macos-latest
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: macOS-latest-cmake-ios
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Build
-        id: cmake_build
-        run: |
-          sysctl -a
-          cmake -B build -G Xcode \
-            -DGGML_METAL_USE_BF16=ON \
-            -DGGML_METAL_EMBED_LIBRARY=ON \
-            -DLLAMA_BUILD_COMMON=OFF \
-            -DLLAMA_BUILD_EXAMPLES=OFF \
-            -DLLAMA_BUILD_TOOLS=OFF \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DLLAMA_BUILD_SERVER=OFF \
-            -DCMAKE_SYSTEM_NAME=iOS \
-            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
-          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
-
-  macOS-latest-cmake-tvos:
-    runs-on: macos-latest
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: macOS-latest-cmake-tvos
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Build
-        id: cmake_build
-        run: |
-          sysctl -a
-          cmake -B build -G Xcode \
-            -DGGML_METAL_USE_BF16=ON \
-            -DGGML_METAL_EMBED_LIBRARY=ON \
-            -DLLAMA_BUILD_COMMON=OFF \
-            -DLLAMA_BUILD_EXAMPLES=OFF \
-            -DLLAMA_BUILD_TOOLS=OFF \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DLLAMA_BUILD_SERVER=OFF \
-            -DCMAKE_SYSTEM_NAME=tvOS \
-            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
-          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
-
-  macOS-latest-cmake-visionos:
-    runs-on: macos-latest
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Build
-        id: cmake_build
-        run: |
-          sysctl -a
-          cmake -B build -G Xcode \
-            -DGGML_METAL_USE_BF16=ON \
-            -DGGML_METAL_EMBED_LIBRARY=ON \
-            -DLLAMA_BUILD_COMMON=OFF \
-            -DLLAMA_BUILD_EXAMPLES=OFF \
-            -DLLAMA_BUILD_TOOLS=OFF \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DLLAMA_BUILD_SERVER=OFF \
-            -DCMAKE_SYSTEM_NAME=visionOS \
-            -DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
-            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
-          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
-
-  macOS-latest-swift:
-    runs-on: macos-latest
-    needs: ios-xcode-build
-
-    strategy:
-      matrix:
-        destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: macOS-latest-swift
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Download xcframework artifact
-        uses: actions/download-artifact@v7
-        with:
-          name: llama-xcframework
-          path: build-apple/llama.xcframework/
-
-      - name: Build llama.cpp with CMake
-        id: cmake_build
-        run: |
-          sysctl -a
-          cmake -B build -G Xcode \
-            -DGGML_METAL_USE_BF16=ON \
-            -DGGML_METAL_EMBED_LIBRARY=ON \
-            -DLLAMA_OPENSSL=OFF \
-            -DLLAMA_BUILD_EXAMPLES=OFF \
-            -DLLAMA_BUILD_TOOLS=OFF \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DLLAMA_BUILD_SERVER=OFF \
-            -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
-          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
-
-  windows-msys2:
-    runs-on: windows-2025
-
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - { sys: UCRT64,  env: ucrt-x86_64,  build: Release }
-          - { sys: CLANG64, env: clang-x86_64, build: Release }
-
-    steps:
-      - name: Clone
-        uses: actions/checkout@v6
-
-      - name: ccache
-        uses: ggml-org/ccache-action@v1.2.16
-        with:
-          key: windows-msys2
-          variant: ccache
-          evict-old-files: 1d
-          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
-      - name: Setup ${{ matrix.sys }}
-        uses: msys2/setup-msys2@v2
-        with:
-          update: true
-          msystem: ${{matrix.sys}}
-          install: >-
-            base-devel
-            git
-            mingw-w64-${{matrix.env}}-toolchain
-            mingw-w64-${{matrix.env}}-cmake
-            mingw-w64-${{matrix.env}}-openblas
-
-      - name: Build using CMake
-        shell: msys2 {0}
-        run: |
-            cmake -B build
-            cmake --build build --config ${{ matrix.build }} -j $(nproc)
-
-      - name: Clean after building using CMake
-        shell: msys2 {0}
-        run: |
-            rm -rf build
-
-      - name: Build using CMake w/ OpenBLAS
-        shell: msys2 {0}
-        run: |
-            cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
-            cmake --build build --config ${{ matrix.build }} -j $(nproc)
-
-  windows-latest-cmake:
+  windows-latest:
     runs-on: windows-2025
 
     env:
@@ -1023,7 +694,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-${{ matrix.build }}
+          key: windows-latest-${{ matrix.build }}
           variant: ccache
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
@@ -1110,7 +781,7 @@ jobs:
       #     $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
       #     & $sde -future -- ctest -L main -C Release --verbose --timeout 900
 
-  ubuntu-latest-cmake-cuda:
+  ubuntu-latest-cuda:
     runs-on: ubuntu-latest
     container: nvidia/cuda:12.6.2-devel-ubuntu24.04
 
@@ -1129,7 +800,7 @@ jobs:
         - name: ccache
           uses: ggml-org/ccache-action@v1.2.16
           with:
-            key: ubuntu-latest-cmake-cuda
+            key: ubuntu-latest-cuda
             evict-old-files: 1d
             save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
@@ -1146,7 +817,7 @@ jobs:
               -DGGML_CUDA_CUB_3DOT2=ON
             cmake --build build
 
-  windows-2022-cmake-cuda:
+  windows-2022-cuda:
     runs-on: windows-2022
 
     strategy:
@@ -1195,7 +866,7 @@ jobs:
           cmake --build build --config Release -j %NINJA_JOBS% -t ggml
           cmake --build build --config Release
 
-  windows-latest-cmake-sycl:
+  windows-latest-sycl:
     runs-on: windows-2022
 
     defaults:
@@ -1214,7 +885,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-sycl
+          key: windows-latest-sycl
           variant: ccache
           evict-old-files: 1d
           save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
@@ -1229,7 +900,7 @@ jobs:
         id: cmake_build
         run:  examples/sycl/win-build-sycl.bat
 
-  windows-latest-cmake-hip:
+  windows-latest-hip:
     runs-on: windows-2022
 
     env:
@@ -1296,223 +967,95 @@ jobs:
             -DGGML_RPC=ON
           cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
 
-  ios-xcode-build:
-    runs-on: macos-latest
+  ubuntu-cpu-riscv64-native:
+    runs-on: RISCV64
 
     steps:
-      - name: Checkout code
-        uses: actions/checkout@v6
-
-      - name: Setup Xcode
-        uses: maxim-lobanov/setup-xcode@v1
-        with:
-          xcode-version: latest-stable
-
-      - name: Build
-        id: cmake_build
+      - name: Install dependencies
         run: |
-          sysctl -a
-          cmake -B build -G Xcode \
-            -DGGML_METAL_USE_BF16=ON \
-            -DGGML_METAL_EMBED_LIBRARY=ON \
-            -DLLAMA_OPENSSL=OFF \
-            -DLLAMA_BUILD_EXAMPLES=OFF \
-            -DLLAMA_BUILD_TOOLS=OFF \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DLLAMA_BUILD_SERVER=OFF \
-            -DCMAKE_SYSTEM_NAME=iOS \
-            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
-          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+          sudo apt-get update
 
-      - name: xcodebuild for swift package
-        id: xcodebuild
-        run: |
-          ./build-xcframework.sh
+          # Install necessary packages
+          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential libssl-dev wget ccache git-lfs
 
-      - name: Upload xcframework artifact
-        uses: actions/upload-artifact@v6
-        with:
-          name: llama-xcframework
-          path: build-apple/llama.xcframework/
-          retention-days: 1
+          # Set gcc-14 and g++-14 as the default compilers
+          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
+          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
+          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
+          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
 
-      - name: Build Xcode project
-        run: |
-          xcodebuild -downloadPlatform iOS
-          xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
+          # Install Rust stable version
+          rustup install stable
+          rustup default stable
 
-  android-build:
-    runs-on: ubuntu-latest
+          git lfs install
 
-    steps:
-      - name: Clone
-        uses: actions/checkout@v6
-
-      # Disabled due to size (400MB) and always 0 cache hits
-      # - name: ccache
-      #   uses: ggml-org/ccache-action@v1.2.16
-      #   with:
-      #     key: android-build
-      #     evict-old-files: 1d
-
-      - name: Set up JDK
-        uses: actions/setup-java@v5
-        with:
-          java-version: 17
-          distribution: zulu
-
-      - name: Setup Android SDK
-        uses: android-actions/setup-android@v3
-        with:
-          log-accepted-android-sdk-licenses: false
-
-      - name: Build
-        run: |
-          cd examples/llama.android
-          ./gradlew build --no-daemon
-
-  android-ndk-build:
-    runs-on: ubuntu-latest
-
-    env:
-      OPENCL_VERSION: 2025.07.22
-
-    strategy:
-      matrix:
-        include:
-          - build: 'arm64-cpu'
-            defines: '-D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=OFF -D GGML_OPENMP=OFF'
-          - build: 'arm64-snapdragon'
-            defines: '--preset arm64-android-snapdragon-release'
-
-    steps:
       - name: Clone
         id: checkout
         uses: actions/checkout@v6
 
-      - name: Install OpenCL Headers and Libs
-        id: install_opencl
-        if: ${{ matrix.build == 'arm64-snapdragon' }}
+      - name: Check environment
         run: |
-          mkdir opencl
-          curl -L -o opencl/clhpp.tar.gz      https://github.com/KhronosGroup/OpenCL-CLHPP/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
-          curl -L -o opencl/headers.tar.gz    https://github.com/KhronosGroup/OpenCL-Headers/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
-          curl -L -o opencl/icd-loader.tar.gz https://github.com/KhronosGroup/OpenCL-ICD-Loader/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
-          tar -xaf opencl/headers.tar.gz    -C opencl
-          tar -xaf opencl/clhpp.tar.gz      -C opencl
-          tar -xaf opencl/icd-loader.tar.gz -C opencl
-          sudo cp -r opencl/OpenCL-Headers-${OPENCL_VERSION}/CL         ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include
-          sudo cp -r opencl/OpenCL-CLHPP-${OPENCL_VERSION}/include/CL/* ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include/CL
-          cd opencl/OpenCL-ICD-Loader-${OPENCL_VERSION}
-          cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -DOPENCL_ICD_LOADER_HEADERS_DIR=${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=31 -DANDROID_STL=c++_shared
-          cmake --build build
-          sudo cp build/libOpenCL.so ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android
-          rm -rf opencl
+          uname -a
+          gcc --version
+          g++ --version
+          ldd --version
+          cmake --version
+          rustc --version
 
-      - name: Install Hexagon SDK
-        id: install_hexsdk
-        if: ${{ matrix.build == 'arm64-snapdragon' }}
-        env:
-          HEXSDK_VER: 6.4.0.2
-          HEXTLS_VER: 19.0.04
+      - name: Setup ccache
         run: |
-          curl -L -o hex-sdk.tar.gz https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v$HEXSDK_VER/hexagon-sdk-v$HEXSDK_VER-amd64-lnx.tar.xz
-          mkdir hex-sdk
-          tar -xaf hex-sdk.tar.gz -C hex-sdk
-          ls -l hex-sdk
-          sudo mv hex-sdk /opt/hexagon
-          echo "HEXAGON_SDK_ROOT=/opt/hexagon/$HEXSDK_VER"                                     >> "$GITHUB_ENV"
-          echo "HEXAGON_TOOLS_ROOT=/opt/hexagon/$HEXSDK_VER/tools/HEXAGON_Tools/$HEXTLS_VER"   >> "$GITHUB_ENV"
-          echo "DEFAULT_HLOS_ARCH=64"                                                          >> "$GITHUB_ENV"
-          echo "DEFAULT_TOOLS_VARIANT=toolv19"                                                 >> "$GITHUB_ENV"
-          echo "DEFAULT_NO_QURT_INC=0"                                                         >> "$GITHUB_ENV"
-          echo "DEFAULT_DSP_ARCH=v73"                                                          >> "$GITHUB_ENV"
+          # Set unique cache directory for this job
+          export CCACHE_DIR="$HOME/.ccache/cpu-cmake-rv64-native"
+          mkdir -p "$CCACHE_DIR"
 
-      - name: Update CMake presets
-        id: update_presets
-        if: ${{ matrix.build == 'arm64-snapdragon' }}
-        run: |
-          cp docs/backend/snapdragon/CMakeUserPresets.json .
+          # Configure ccache for optimal performance
+          ccache --set-config=max_size=5G
+          ccache --set-config=compression=true
+          ccache --set-config=compression_level=6
+          ccache --set-config=cache_dir="$CCACHE_DIR"
+
+          # Enable more aggressive caching
+          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
+          ccache --set-config=hash_dir=false
+
+          # Export for subsequent steps
+          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
+          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
 
       - name: Build
-        id: ndk_build
+        id: cmake_build
         run: |
-          cmake ${{ matrix.defines }} -B build
-          cmake --build build
-          cmake --install build --prefix pkg-adb/llama.cpp
+          cmake -B build \
+            -DCMAKE_BUILD_TYPE=Release \
+            -DGGML_OPENMP=OFF \
+            -DLLAMA_BUILD_EXAMPLES=ON \
+            -DLLAMA_BUILD_TOOLS=ON \
+            -DLLAMA_BUILD_TESTS=ON \
+            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DGGML_RPC=ON \
+            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
+            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
+
+          cmake --build build --config Release -j $(nproc)
 
       - name: Test
         id: cmake_test
         run: |
-          echo "FIXME: test on devices"
+          cd build
+          ctest -L main --verbose --timeout 900
 
-  openEuler-latest-cmake-cann:
-    defaults:
-      run:
-        shell: bash -el {0}
-    strategy:
-      matrix:
-        arch: [x86, aarch64]
-        chip_type: ['910b', '310p']
-        build: ['Release']
-        use_acl_graph: ['on', 'off']
-        exclude:
-          # 310P does not support USE_ACL_GRAPH=on
-          - chip_type: '310p'
-            use_acl_graph: 'on'
-    runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Free up disk space
-        uses: ggml-org/free-disk-space@v1.3.1
-        with:
-          tool-cache: true
-
-      - name: Set container image
-        id: cann-image
+      - name: Test llama2c conversion
+        id: llama2c_test
         run: |
-          image="ascendai/cann:${{ matrix.chip_type == '910b' &&  '8.3.rc2-910b-openeuler24.03-py3.11' || '8.3.rc2-310p-openeuler24.03-py3.11' }}"
-          echo "image=${image}" >> "${GITHUB_OUTPUT}"
-
-      - name: Pull container image
-        run: docker pull "${{ steps.cann-image.outputs.image }}"
-
-      - name: Build
-        env:
-          BUILD_TYPE: ${{ matrix.build }}
-          SOC_TYPE: ascend${{ matrix.chip_type }}
-          USE_ACL_GRAPH: ${{ matrix.use_acl_graph }}
-        run: |
-          HOST_UID=$(id -u)
-          HOST_GID=$(id -g)
-
-          docker run --rm \
-            -v "${PWD}:/workspace" \
-            -w /workspace \
-            -e SOC_TYPE=${SOC_TYPE} \
-            -e BUILD_TYPE=${BUILD_TYPE} \
-            -e USE_ACL_GRAPH=${USE_ACL_GRAPH} \
-            "${{ steps.cann-image.outputs.image }}" \
-            bash -lc '
-              set -e
-              yum install -y --setopt=install_weak_deps=False --setopt=tsflags=nodocs git gcc gcc-c++ make cmake openssl-devel
-              yum clean all && rm -rf /var/cache/yum
-              git config --global --add safe.directory "/workspace"
-              export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH}
-              cmake -S . -B build \
-                  -DCMAKE_BUILD_TYPE=${BUILD_TYPE} \
-                  -DGGML_CANN=on \
-                  -DSOC_TYPE=${SOC_TYPE} \
-                  -DUSE_ACL_GRAPH=${USE_ACL_GRAPH}
-              cmake --build build -j $(nproc)
-
-              chown -R '"${HOST_UID}"':'"${HOST_GID}"' /workspace/build
-            '
+          cd build
+          echo "Fetch tokenizer"
+          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
+          echo "Fetch llama2c model"
+          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
+          ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
+          ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
 # TODO: simplify the following workflows using a matrix
 # TODO: run lighter CI on PRs and the full CI only on master (if needed)
@@ -1672,342 +1215,7 @@ jobs:
          run: |
            GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
 
-  ubuntu-cpu-cmake-riscv64-native:
-    runs-on: RISCV64
-
-    steps:
-      - name: Install dependencies
-        run: |
-          sudo apt-get update
-
-          # Install necessary packages
-          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential libssl-dev wget ccache git-lfs
-
-          # Set gcc-14 and g++-14 as the default compilers
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
-          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
-          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
-          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
-
-          # Install Rust stable version
-          rustup install stable
-          rustup default stable
-
-          git lfs install
-
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Check environment
-        run: |
-          uname -a
-          gcc --version
-          g++ --version
-          ldd --version
-          cmake --version
-          rustc --version
-
-      - name: Setup ccache
-        run: |
-          # Set unique cache directory for this job
-          export CCACHE_DIR="$HOME/.ccache/cpu-cmake-rv64-native"
-          mkdir -p "$CCACHE_DIR"
-
-          # Configure ccache for optimal performance
-          ccache --set-config=max_size=5G
-          ccache --set-config=compression=true
-          ccache --set-config=compression_level=6
-          ccache --set-config=cache_dir="$CCACHE_DIR"
-
-          # Enable more aggressive caching
-          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
-          ccache --set-config=hash_dir=false
-
-          # Export for subsequent steps
-          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
-          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
-
-      - name: Build
-        id: cmake_build
-        run: |
-          cmake -B build \
-            -DCMAKE_BUILD_TYPE=Release \
-            -DGGML_OPENMP=OFF \
-            -DLLAMA_BUILD_EXAMPLES=ON \
-            -DLLAMA_BUILD_TOOLS=ON \
-            -DLLAMA_BUILD_TESTS=ON \
-            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-            -DGGML_RPC=ON \
-            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
-
-          cmake --build build --config Release -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose --timeout 900
-
-      - name: Test llama2c conversion
-        id: llama2c_test
-        run: |
-          cd build
-          echo "Fetch tokenizer"
-          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
-          echo "Fetch llama2c model"
-          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
-          ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
-          ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
-
-  ubuntu-cmake-sanitizer-riscv64-native:
-    runs-on: RISCV64
-
-    continue-on-error: true
-
-    strategy:
-      matrix:
-        sanitizer: [ADDRESS, THREAD, UNDEFINED]
-        build_type: [Debug]
-
-    steps:
-      - name: Install dependencies
-        run: |
-          sudo apt-get update
-
-          # Install necessary packages
-          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
-
-          # Set gcc-14 and g++-14 as the default compilers
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
-          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
-          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
-          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
-
-          # Install Rust stable version
-          rustup install stable
-          rustup default stable
-
-          git lfs install
-
-      - name: GCC version check
-        run: |
-          gcc --version
-          g++ --version
-
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Setup ccache
-        run: |
-          # Unique cache directory per matrix combination
-          export CCACHE_DIR="$HOME/.ccache/sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}"
-          mkdir -p "$CCACHE_DIR"
-
-          # Configure ccache
-          ccache --set-config=max_size=5G
-          ccache --set-config=compression=true
-          ccache --set-config=compression_level=6
-          ccache --set-config=cache_dir="$CCACHE_DIR"
-          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
-          ccache --set-config=hash_dir=false
-
-          # Export for subsequent steps
-          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
-          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
-
-      - name: Build
-        id: cmake_build
-        if: ${{ matrix.sanitizer != 'THREAD' }}
-        run: |
-          cmake -B build \
-            -DLLAMA_OPENSSL=OFF \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DGGML_OPENMP=ON \
-            -DLLAMA_BUILD_EXAMPLES=ON \
-            -DLLAMA_BUILD_TOOLS=ON \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
-
-          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
-
-      - name: Build (no OpenMP)
-        id: cmake_build_no_openmp
-        if: ${{ matrix.sanitizer == 'THREAD' }}
-        run: |
-          cmake -B build \
-            -DLLAMA_OPENSSL=OFF \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DGGML_OPENMP=OFF \
-            -DLLAMA_BUILD_EXAMPLES=ON \
-            -DLLAMA_BUILD_TOOLS=ON \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
-
-          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose --timeout 900
-
-
-  ubuntu-llguidance-riscv64-native:
-    runs-on: RISCV64
-    steps:
-      - name: Install dependencies
-        run: |
-          sudo apt-get update
-
-          # Install necessary packages
-          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
-
-          # Set gcc-14 and g++-14 as the default compilers
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
-          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
-          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
-          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
-
-          # Install Rust stable version
-          rustup install stable
-          rustup default stable
-
-          git lfs install
-
-      - name: GCC version check
-        run: |
-          gcc --version
-          g++ --version
-
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Setup ccache
-        run: |
-          export CCACHE_DIR="$HOME/.ccache/llguidance-riscv64"
-          mkdir -p "$CCACHE_DIR"
-
-          ccache --set-config=max_size=5G
-          ccache --set-config=compression=true
-          ccache --set-config=compression_level=6
-          ccache --set-config=cache_dir="$CCACHE_DIR"
-          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
-          ccache --set-config=hash_dir=false
-
-          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
-          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
-
-      - name: Build
-        id: cmake_build
-        run: |
-          cmake -B build \
-            -DLLAMA_OPENSSL=OFF \
-            -DCMAKE_BUILD_TYPE=Release \
-            -DGGML_OPENMP=OFF \
-            -DLLAMA_BUILD_EXAMPLES=ON \
-            -DLLAMA_BUILD_TOOLS=ON \
-            -DLLAMA_BUILD_TESTS=OFF \
-            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-            -DLLAMA_LLGUIDANCE=ON \
-            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
-
-          cmake --build build --config Release -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose --timeout 900
-
-
-  ubuntu-cmake-rpc-riscv64-native:
-    runs-on: RISCV64
-
-    continue-on-error: true
-
-    steps:
-      - name: Install dependencies
-        run: |
-          sudo apt-get update
-
-          # Install necessary packages
-          sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential libssl-dev wget ccache git-lfs
-
-          # Set gcc-14 and g++-14 as the default compilers
-          sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
-          sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
-          sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
-          sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
-
-          # Install Rust stable version
-          rustup install stable
-          rustup default stable
-
-          git lfs install
-
-      - name: GCC version check
-        run: |
-          gcc --version
-          g++ --version
-
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v6
-
-      - name: Setup ccache
-        run: |
-          export CCACHE_DIR="$HOME/.ccache/rpc-riscv64"
-          mkdir -p "$CCACHE_DIR"
-
-          ccache --set-config=max_size=5G
-          ccache --set-config=compression=true
-          ccache --set-config=compression_level=6
-          ccache --set-config=cache_dir="$CCACHE_DIR"
-          ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
-          ccache --set-config=hash_dir=false
-
-          echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
-          echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
-
-      - name: Build
-        id: cmake_build
-        run: |
-          cmake -B build \
-            -DCMAKE_BUILD_TYPE=Release \
-            -DGGML_OPENMP=OFF \
-            -DLLAMA_BUILD_EXAMPLES=ON \
-            -DLLAMA_BUILD_TOOLS=ON \
-            -DLLAMA_BUILD_TESTS=ON \
-            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-            -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-            -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
-            -DGGML_RPC=ON
-
-          cmake --build build --config Release -j $(nproc)
-
-      - name: Test
-        id: cmake_test
-        run: |
-          cd build
-          ctest -L main --verbose
-
-  ggml-ci-arm64-graviton4-kleidiai:
+  ggml-ci-arm64-cpu-kleidiai-graviton4:
      runs-on: ah-ubuntu_22_04-c8g_8x
 
      steps:
@@ -2044,7 +1252,7 @@ jobs:
        - name: ccache
          uses: ggml-org/ccache-action@v1.2.16
          with:
-           key: ggml-ci-arm64-graviton4-kleidiai
+           key: ggml-ci-arm64-cpu-kleidiai-graviton4
            evict-old-files: 1d
            save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
diff --git a/.github/workflows/python-lint.yml b/.github/workflows/python-lint.yml
index 8d1dd7a7d5..e21b3b6568 100644
--- a/.github/workflows/python-lint.yml
+++ b/.github/workflows/python-lint.yml
@@ -4,10 +4,16 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/python-lint.yml', '**/*.py']
+    paths: [
+      '.github/workflows/python-lint.yml',
+      '**/*.py'
+    ]
   pull_request:
     types: [opened, synchronize, reopened]
-    paths: ['.github/workflows/python-lint.yml', '**/*.py']
+    paths: [
+      '.github/workflows/python-lint.yml',
+      '**/*.py'
+    ]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index f329630071..b0f2714ffd 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -10,7 +10,22 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/release.yml', '**/CMakeLists.txt', '**/.cmake', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp']
+    paths: [
+      '.github/workflows/release.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.cu',
+      '**/*.cuh',
+      '**/*.swift',
+      '**/*.m',
+      '**/*.metal',
+      '**/*.comp',
+      '**/*.glsl'
+    ]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
@@ -34,7 +49,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: macOS-latest-cmake-arm64
+          key: macOS-latest-arm64
           evict-old-files: 1d
 
       - name: Build
@@ -81,7 +96,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: macOS-latest-cmake-x64
+          key: macOS-latest-x64
           evict-old-files: 1d
 
       - name: Build
@@ -140,7 +155,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-cpu-cmake-${{ matrix.build }}
+          key: ubuntu-cpu-${{ matrix.build }}
           evict-old-files: 1d
 
       - name: Dependencies
@@ -191,7 +206,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-22-cmake-vulkan
+          key: ubuntu-22-vulkan
           evict-old-files: 1d
 
       - name: Dependencies
@@ -256,7 +271,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-24-cmake-openvino-release-no-preset-v1
+          key: ubuntu-24-openvino-release-no-preset-v1
           evict-old-files: 1d
 
       - name: Dependencies
@@ -329,7 +344,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-cpu-${{ matrix.arch }}
+          key: windows-latest-cpu-${{ matrix.arch }}
           variant: ccache
           evict-old-files: 1d
 
@@ -390,7 +405,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-${{ matrix.backend }}-${{ matrix.arch }}
+          key: windows-latest-${{ matrix.backend }}-${{ matrix.arch }}
           variant: ccache
           evict-old-files: 1d
 
@@ -536,7 +551,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-sycl
+          key: windows-latest-sycl
           variant: ccache
           evict-old-files: 1d
 
@@ -616,7 +631,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: ubuntu-rocm-cmake-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}
+          key: ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}
           evict-old-files: 1d
 
       - name: Dependencies
@@ -726,7 +741,7 @@ jobs:
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.16
         with:
-          key: windows-latest-cmake-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}-x64
+          key: windows-latest-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}-x64
           evict-old-files: 1d
 
       - name: Install ROCm
diff --git a/.github/workflows/server-sanitize.yml b/.github/workflows/server-sanitize.yml
new file mode 100644
index 0000000000..4c9f447cf8
--- /dev/null
+++ b/.github/workflows/server-sanitize.yml
@@ -0,0 +1,105 @@
+name: Server (sanitize)
+
+on:
+  workflow_dispatch: # allows manual triggering
+    inputs:
+      sha:
+        description: 'Commit SHA1 to build'
+        required: false
+        type: string
+      slow_tests:
+        description: 'Run slow tests'
+        required: true
+        type: boolean
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/server-sanitize.yml',
+      '**/CMakeLists.txt',
+      '**/Makefile',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      'tools/server/**.*'
+    ]
+
+env:
+  LLAMA_LOG_COLORS: 1
+  LLAMA_LOG_PREFIX: 1
+  LLAMA_LOG_TIMESTAMPS: 1
+  LLAMA_LOG_VERBOSITY: 10
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  server:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
+        build_type: [RelWithDebInfo]
+      fail-fast: false
+
+    steps:
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get -y install \
+            build-essential \
+            xxd \
+            git \
+            cmake \
+            curl \
+            wget \
+            language-pack-en \
+            libssl-dev
+
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
+
+      - name: Build
+        id: cmake_build
+        run: |
+          cmake -B build \
+            -DLLAMA_BUILD_BORINGSSL=ON \
+            -DGGML_SCHED_NO_REALLOC=ON \
+            -DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
+            -DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
+            -DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
+            -DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
+            -DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
+            -DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
+          cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
+
+      - name: Python setup
+        id: setup_python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+          pip-install: -r tools/server/tests/requirements.txt
+
+      - name: Tests
+        id: server_integration_tests
+        if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
+        run: |
+          cd tools/server/tests
+          export ${{ matrix.extra_args }}
+          pytest -v -x -m "not slow"
+
+      - name: Slow tests
+        id: server_integration_tests_slow
+        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
+        run: |
+          cd tools/server/tests
+          export ${{ matrix.extra_args }}
+          SLOW_TESTS=1 pytest -v -x
diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.yml
index a11aea7e89..29bd79690a 100644
--- a/.github/workflows/server-self-hosted.yml
+++ b/.github/workflows/server-self-hosted.yml
@@ -14,7 +14,19 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/server-self-hosted.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
+    paths: [
+      '.github/workflows/server-self-hosted.yml',
+      '**/CMakeLists.txt',
+      '**/Makefile',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.cu',
+      '**/*.swift',
+      '**/*.m',
+      'tools/server/**.*'
+    ]
 
 env:
   LLAMA_LOG_COLORS: 1
diff --git a/.github/workflows/server-webui.yml b/.github/workflows/server-webui.yml
index 4d560ff58d..492107ffd8 100644
--- a/.github/workflows/server-webui.yml
+++ b/.github/workflows/server-webui.yml
@@ -1,4 +1,3 @@
-# Server WebUI build and tests
 name: Server WebUI
 
 on:
@@ -11,10 +10,20 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/server-webui.yml', 'tools/server/webui/**.*', 'tools/server/tests/**.*', 'tools/server/public/**']
+    paths: [
+      '.github/workflows/server-webui.yml',
+      'tools/server/webui/**.*',
+      'tools/server/tests/**.*',
+      'tools/server/public/**'
+    ]
   pull_request:
     types: [opened, synchronize, reopened]
-    paths: ['.github/workflows/server-webui.yml', 'tools/server/webui/**.*', 'tools/server/tests/**.*', 'tools/server/public/**']
+    paths: [
+      '.github/workflows/server-webui.yml',
+      'tools/server/webui/**.*',
+      'tools/server/tests/**.*',
+      'tools/server/public/**'
+    ]
 
 env:
   LLAMA_LOG_COLORS: 1
diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml
index 99d05226ba..750c29f08e 100644
--- a/.github/workflows/server.yml
+++ b/.github/workflows/server.yml
@@ -1,4 +1,3 @@
-# Server build and tests
 name: Server
 
 on:
@@ -15,10 +14,34 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
+    paths: [
+      '.github/workflows/server.yml',
+      '**/CMakeLists.txt',
+      '**/Makefile',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.cu',
+      '**/*.swift',
+      '**/*.m',
+      'tools/server/**.*'
+    ]
   pull_request:
     types: [opened, synchronize, reopened]
-    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
+    paths: [
+      '.github/workflows/server.yml',
+      '**/CMakeLists.txt',
+      '**/Makefile',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.cu',
+      '**/*.swift',
+      '**/*.m',
+      'tools/server/**.*'
+    ]
 
 env:
   LLAMA_LOG_COLORS: 1
@@ -34,17 +57,18 @@ jobs:
   server:
     runs-on: ubuntu-latest
 
+    name: server (${{ matrix.wf_name }})
     strategy:
       matrix:
-        sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
-        build_type: [RelWithDebInfo]
+        build_type: [Release]
+        wf_name: ["default"]
         include:
           - build_type: Release
-            sanitizer: ""
             extra_args: ""
+            wf_name:    "default"
           - build_type: Release
-            sanitizer: ""
             extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
+            wf_name:    "backend-sampling"
       fail-fast: false
 
     steps:
@@ -74,13 +98,7 @@ jobs:
         run: |
           cmake -B build \
             -DLLAMA_BUILD_BORINGSSL=ON \
-            -DGGML_SCHED_NO_REALLOC=ON \
-            -DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-            -DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-            -DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
-            -DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-            -DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-            -DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
+            -DGGML_SCHED_NO_REALLOC=ON
           cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
 
       - name: Python setup
diff --git a/CODEOWNERS b/CODEOWNERS
index 29673a7b26..4257f5927a 100644
--- a/CODEOWNERS
+++ b/CODEOWNERS
@@ -2,29 +2,13 @@
 # multiplie collaborators per item can be specified
 
 /.devops/*.Dockerfile                   @ngxson
-/.github/actions/                       @CISC
-/.github/workflows/                     @CISC
+/.github/actions/                       @ggml-org/ci
+/.github/workflows/                     @ggml-org/ci
 /ci/                                    @ggerganov
 /cmake/                                 @ggerganov
-/common/CMakeLists.txt                  @ggerganov
-/common/arg.*                           @ggerganov
-/common/base64.hpp.*                    @ggerganov
-/common/build-info.*                    @ggerganov
-/common/chat.*                          @pwilkin
-/common/chat-auto*.*                    @pwilkin
-/common/chat-diff-analyzer.*            @pwilkin
-/common/chat-peg-parser.*               @aldehir
-/common/common.*                        @ggerganov
-/common/console.*                       @ggerganov
-/common/http.*                          @angt
-/common/jinja/                          @ngxson @CISC @aldehir
-/common/llguidance.*                    @ggerganov
-/common/log.*                           @ggerganov
+/common/                                @ggml-org/llama-common
+/common/jinja/                          @CISC
 /common/ngram-map.*                     @srogmann
-/common/peg-parser.*                    @aldehir
-/common/sampling.*                      @ggerganov
-/common/speculative.*                   @ggerganov
-/common/unicode.*                       @aldehir
 /convert_*.py                           @CISC
 /examples/batched.swift/                @ggerganov
 /examples/batched/                      @ggerganov
@@ -51,29 +35,27 @@
 /examples/speculative/                  @ggerganov
 /ggml/cmake/                            @ggerganov
 /ggml/include/                          @ggerganov
+/ggml/src/ggml-cann/                    @ggml-org/ggml-cann
 /ggml/src/ggml-common.h                 @ggerganov
 /ggml/src/ggml-cpu/                     @ggerganov
 /ggml/src/ggml-cpu/spacemit/            @alex-spacemit
-/ggml/src/ggml-cuda/fattn*              @JohannesGaessler
-/ggml/src/ggml-cuda/mmf.*               @JohannesGaessler @am17an
-/ggml/src/ggml-cuda/mmq.*               @JohannesGaessler
-/ggml/src/ggml-cuda/mmvf.*              @JohannesGaessler
-/ggml/src/ggml-cuda/mmvq.*              @JohannesGaessler
+/ggml/src/ggml-cuda/                    @ggml-org/ggml-cuda
 /ggml/src/ggml-cuda/fattn-wmma*         @IMbackK
 /ggml/src/ggml-hip/                     @IMbackK
 /ggml/src/ggml-cuda/vendors/hip.h       @IMbackK
 /ggml/src/ggml-impl.h                   @ggerganov
-/ggml/src/ggml-metal/                   @ggerganov
-/ggml/src/ggml-opencl/                  @lhez @max-krasnyansky
-/ggml/src/ggml-hexagon/                 @max-krasnyansky @lhez
+/ggml/src/ggml-metal/                   @ggml-org/ggml-metal
+/ggml/src/ggml-opencl/                  @ggml-org/ggml-opencl
+/ggml/src/ggml-hexagon/                 @ggml-org/ggml-hexagon
 /ggml/src/ggml-opt.cpp                  @JohannesGaessler
 /ggml/src/ggml-quants.*                 @ggerganov
-/ggml/src/ggml-rpc/                     @rgerganov
+/ggml/src/ggml-rpc/                     @ggml-org/ggml-rpc
+/ggml/src/ggml-sycl/                    @ggml-org/ggml-sycl
 /ggml/src/ggml-threading.*              @ggerganov
-/ggml/src/ggml-vulkan/                  @0cc4m
+/ggml/src/ggml-vulkan/                  @ggml-org/ggml-vulkan
 /ggml/src/ggml-virtgpu/                 @kpouget
-/ggml/src/ggml-webgpu/                  @reeselevine
-/ggml/src/ggml-zdnn/                    @taronaeo @Andreas-Krebbel @AlekseiNikiforovIBM
+/ggml/src/ggml-webgpu/                  @ggml-org/ggml-webgpu
+/ggml/src/ggml-zdnn/                    @ggml-org/ggml-zdnn @Andreas-Krebbel @AlekseiNikiforovIBM
 /ggml/src/ggml-openvino/                @cavusmustafa @wine99
 /ggml/src/ggml.c                        @ggerganov
 /ggml/src/ggml.cpp                      @ggerganov
@@ -93,16 +75,18 @@
 /src/models/                            @CISC
 /tests/                                 @ggerganov
 /tests/test-chat.*                      @pwilkin
+/tests/test-llama-archs.cpp             @JohannesGaessler
 /tools/batched-bench/                   @ggerganov
 /tools/cli/                             @ngxson
 /tools/completion/                      @ggerganov
-/tools/mtmd/                            @ngxson
+/tools/mtmd/                            @ggml-org/llama-mtmd
 /tools/perplexity/                      @ggerganov
 /tools/parser/                          @pwilkin
 /tools/quantize/                        @ggerganov
-/tools/rpc/                             @rgerganov
-/tools/server/*                         @ngxson @ggerganov # no subdir
-/tools/server/webui/                    @allozaur
+/tools/rpc/                             @ggml-org/ggml-rpc
+/tools/server/*                         @ggml-org/llama-server # no subdir
+/tools/server/tests/                    @ggml-org/llama-server
+/tools/server/webui/                    @ggml-org/llama-webui
 /tools/tokenize/                        @ggerganov
 /tools/tts/                             @ggerganov
 /vendor/                                @ggerganov
diff --git a/common/chat-diff-analyzer.cpp b/common/chat-diff-analyzer.cpp
index 4068340a5c..05b3b6b6a8 100644
--- a/common/chat-diff-analyzer.cpp
+++ b/common/chat-diff-analyzer.cpp
@@ -479,6 +479,7 @@ analyze_content::analyze_content(const common_chat_template & tmpl, const analyz
 
     if (!comparison_with_tools || !comparison_with_reasoning) {
         LOG_DBG(ANSI_ORANGE "%s: Template application failed\n" ANSI_RESET, __func__);
+        return;
     }
 
     const auto & diff_tools     = comparison_with_tools->diff;
@@ -911,8 +912,10 @@ void analyze_tools::extract_function_markers() {
             // we'll have to rely on an extra diff with no-calls version
             auto notool_comp = compare_variants(
                 *tmpl, params, [&](template_params & p) { p.messages = json::array({ user_msg, assistant_nocall }); });
-            auto nt_diff  = notool_comp->diff;
-            closer_suffix = nt_diff.left.substr(nt_diff.left.find("YYYY") + 4);
+            if (notool_comp) {
+                auto nt_diff  = notool_comp->diff;
+                closer_suffix = nt_diff.left.substr(nt_diff.left.find("YYYY") + 4);
+            }
         } else {
             closer_suffix = diff.suffix.substr(0, diff.suffix.find(suffix_marker));
         }
diff --git a/ggml/src/ggml-cuda/fattn-common.cuh b/ggml/src/ggml-cuda/fattn-common.cuh
index b6a7460da8..e9abdf288c 100644
--- a/ggml/src/ggml-cuda/fattn-common.cuh
+++ b/ggml/src/ggml-cuda/fattn-common.cuh
@@ -892,7 +892,7 @@ void launch_fattn(
     const int ntiles_x     = ((Q->ne[1] + ncols1 - 1) / ncols1);
     const int gqa_ratio    = Q->ne[2] / K->ne[2];
     const int ntiles_z_gqa = ((gqa_ratio + ncols2 - 1) / ncols2);
-    const int ntiles_total = ntiles_x * ntiles_z_gqa * K->ne[2] * Q->ne[3];
+    const int ntiles_dst   = ntiles_x * ntiles_z_gqa * K->ne[2] * Q->ne[3];
 
     // Optional optimization where the mask is scanned to determine whether part of the calculation can be skipped.
     // Only worth the overhead if there is at lease one FATTN_KQ_STRIDE x FATTN_KQ_STRIDE square to be skipped or
@@ -919,37 +919,37 @@ void launch_fattn(
     GGML_ASSERT(max_blocks_per_sm > 0);
     int parallel_blocks = max_blocks_per_sm;
 
+    const int ntiles_KV = (K->ne[1] + nbatch_fa - 1) / nbatch_fa; // Max. number of parallel blocks limited by KV cache length.
+
     dim3 blocks_num;
     if (stream_k) {
         // For short contexts it can be faster to have the SMs work on whole tiles because this lets us skip the fixup.
         const int max_blocks = max_blocks_per_sm*nsm;
-        const int tiles_nwaves = (ntiles_total + max_blocks - 1) / max_blocks;
-        const int tiles_efficiency_percent = 100 * ntiles_total / (max_blocks*tiles_nwaves);
+        const int tiles_nwaves = (ntiles_dst + max_blocks - 1) / max_blocks;
+        const int tiles_efficiency_percent = 100 * ntiles_dst / (max_blocks*tiles_nwaves);
 
-        const int nblocks_stream_k = max_blocks;
+        const int nblocks_stream_k = std::min(max_blocks, ntiles_KV*ntiles_dst);
 
         const bool use_stream_k = cc >= GGML_CUDA_CC_ADA_LOVELACE || amd_wmma_available(cc) || tiles_efficiency_percent < 75;
 
-        blocks_num.x = use_stream_k ? nblocks_stream_k : ntiles_total;
+        blocks_num.x = use_stream_k ? nblocks_stream_k : ntiles_dst;
         blocks_num.y = 1;
         blocks_num.z = 1;
 
-        if (ntiles_total % blocks_num.x != 0) { // Fixup is only needed if the SMs work on fractional tiles.
+        if (ntiles_dst % blocks_num.x != 0) { // Fixup is only needed if the SMs work on fractional tiles.
             dst_tmp_meta.alloc((size_t(blocks_num.x) * ncols * (2 + DV/2)));
         }
     } else {
-        const int ntiles_KQ = (K->ne[1] + nbatch_fa - 1) / nbatch_fa; // Max. number of parallel blocks limited by tensor size.
-
         // parallel_blocks must not be larger than what the tensor size allows:
-        parallel_blocks = std::min(parallel_blocks, ntiles_KQ);
+        parallel_blocks = std::min(parallel_blocks, ntiles_KV);
 
         // If ntiles_total % blocks_per_wave != 0 then some efficiency is lost due to tail effects.
         // Test whether parallel_blocks can be set to a higher value for better efficiency.
         const int blocks_per_wave = nsm * max_blocks_per_sm;
         int nwaves_best = 0;
         int efficiency_percent_best = 0;
-        for (int parallel_blocks_test = parallel_blocks; parallel_blocks_test <= ntiles_KQ; ++parallel_blocks_test) {
-            const int nblocks_total = ntiles_total * parallel_blocks_test;
+        for (int parallel_blocks_test = parallel_blocks; parallel_blocks_test <= ntiles_KV; ++parallel_blocks_test) {
+            const int nblocks_total = ntiles_dst * parallel_blocks_test;
             const int nwaves = (nblocks_total + blocks_per_wave - 1) / blocks_per_wave;
             const int efficiency_percent = 100 * nblocks_total / (nwaves*blocks_per_wave);
 
@@ -1015,7 +1015,7 @@ void launch_fattn(
     CUDA_CHECK(cudaGetLastError());
 
     if (stream_k) {
-        if (ntiles_total % blocks_num.x != 0) { // Fixup is only needed if the SMs work on fractional tiles.
+        if (ntiles_dst % blocks_num.x != 0) { // Fixup is only needed if the SMs work on fractional tiles.
             const dim3 block_dim_combine(DV, 1, 1);
             const dim3 blocks_num_combine = {blocks_num.x, ncols1, ncols2};
 
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index ce7a80acde..5a0be4a472 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -124,7 +124,10 @@ static cudaError_t ggml_cuda_device_malloc(void ** ptr, size_t size, int device)
         err = cudaMallocManaged(ptr, size);
 #if defined(GGML_USE_HIP)
         if (err == hipSuccess) {
-            CUDA_CHECK(cudaMemAdvise(*ptr, size, hipMemAdviseSetCoarseGrain, device));
+            // hipMemAdviseSetCoarseGrain is an optional performance hint;
+            // ignore errors (e.g. hipErrorInvalidValue on some APU/iGPU configs).
+            cudaMemAdvise(*ptr, size, hipMemAdviseSetCoarseGrain, device);
+            (void)hipGetLastError(); // clear any error
         }
 
         // fall back to cudaMalloc if not supported (e.g. on Windows)
@@ -251,11 +254,6 @@ static ggml_cuda_device_info ggml_cuda_init() {
         info.devices[id].supports_cooperative_launch = false;
 #endif // !(GGML_USE_MUSA)
 
-        // cudaMemGetInfo returns info for the current device
-        size_t free_mem;
-        CUDA_CHECK(cudaSetDevice(id));
-        CUDA_CHECK(cudaMemGetInfo(&free_mem, NULL));
-
 #if defined(GGML_USE_HIP)
         info.devices[id].smpbo = prop.sharedMemPerBlock;
 
@@ -270,25 +268,25 @@ static ggml_cuda_device_info ggml_cuda_init() {
                 info.devices[id].cc += prop.minor * 0x10;
             }
         }
-        GGML_LOG_INFO("  Device %d: %s, %s (0x%x), VMM: %s, Wave Size: %d, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, %s (0x%x), VMM: %s, Wave Size: %d, VRAM: %zu MiB\n",
                       id, prop.name, prop.gcnArchName, info.devices[id].cc & 0xffff,
                       device_vmm ? "yes" : "no", prop.warpSize,
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
 #elif defined(GGML_USE_MUSA)
         // FIXME: Ensure compatibility with varying warp sizes across different MUSA archs.
         info.devices[id].warp_size = 32;
         info.devices[id].smpbo = prop.sharedMemPerBlockOptin;
         info.devices[id].cc = GGML_CUDA_CC_OFFSET_MTHREADS + prop.major * 0x100;
         info.devices[id].cc += prop.minor * 0x10;
-        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB\n",
                       id, prop.name, prop.major, prop.minor, device_vmm ? "yes" : "no",
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
 #else
         info.devices[id].smpbo = prop.sharedMemPerBlockOptin;
         info.devices[id].cc = 100*prop.major + 10*prop.minor;
-        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB\n",
                       id, prop.name, prop.major, prop.minor, device_vmm ? "yes" : "no",
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
         std::string device_name(prop.name);
         if (device_name == "NVIDIA GeForce MX450") {
             turing_devices_without_mma.push_back({ id, device_name });
@@ -303,6 +301,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
         // TODO: Check for future drivers the default scheduling strategy and
         // remove this call again when cudaDeviceScheduleSpin is default.
         if (prop.major == 12 && prop.minor == 1) {
+            CUDA_CHECK(cudaSetDevice(id));
             CUDA_CHECK(cudaSetDeviceFlags(cudaDeviceScheduleSpin));
         }
 
diff --git a/ggml/src/ggml-sycl/gated_delta_net.cpp b/ggml/src/ggml-sycl/gated_delta_net.cpp
index 8c76afbd57..648455c134 100644
--- a/ggml/src/ggml-sycl/gated_delta_net.cpp
+++ b/ggml/src/ggml-sycl/gated_delta_net.cpp
@@ -55,7 +55,7 @@ void gated_delta_net_sycl(const float *     q,
 #pragma unroll
     for (int r = 0; r < rows_per_lane; r++) {
         const int i = r * warp_size + lane;
-        s_shard[r]  = curr_state[i * S_v + col];
+        s_shard[r]  = curr_state[col * S_v + i];
     }
 
     for (int t = 0; t < n_tokens; t++) {
@@ -137,7 +137,7 @@ void gated_delta_net_sycl(const float *     q,
 #pragma unroll
     for (int r = 0; r < rows_per_lane; r++) {
         const int i          = r * warp_size + lane;
-        state[i * S_v + col] = s_shard[r];
+        state[col * S_v + i] = s_shard[r];
     }
 }
 
diff --git a/scripts/sync_vendor.py b/scripts/sync_vendor.py
index 1a87d73563..4d254afcd6 100755
--- a/scripts/sync_vendor.py
+++ b/scripts/sync_vendor.py
@@ -5,7 +5,7 @@ import os
 import sys
 import subprocess
 
-HTTPLIB_VERSION = "refs/tags/v0.37.2"
+HTTPLIB_VERSION = "refs/tags/v0.38.0"
 
 vendor = {
     "https://github.com/nlohmann/json/releases/latest/download/json.hpp":     "vendor/nlohmann/json.hpp",
diff --git a/tools/server/tests/unit/test_completion.py b/tools/server/tests/unit/test_completion.py
index 2a980601ec..61042da55c 100644
--- a/tools/server/tests/unit/test_completion.py
+++ b/tools/server/tests/unit/test_completion.py
@@ -563,7 +563,7 @@ def test_cancel_request():
     except requests.exceptions.ReadTimeout:
         pass # expected
     # make sure the slot is free
-    time.sleep(1) # wait for HTTP_POLLING_SECONDS
+    time.sleep(2)
     res = server.make_request("GET", "/slots")
     assert res.body[0]["is_processing"] == False
 
diff --git a/vendor/cpp-httplib/httplib.cpp b/vendor/cpp-httplib/httplib.cpp
index 41e7a361c0..fa0718218e 100644
--- a/vendor/cpp-httplib/httplib.cpp
+++ b/vendor/cpp-httplib/httplib.cpp
@@ -1025,6 +1025,30 @@ bool is_valid_path(const std::string &path) {
   return true;
 }
 
+bool canonicalize_path(const char *path, std::string &resolved) {
+#if defined(_WIN32)
+  char buf[_MAX_PATH];
+  if (_fullpath(buf, path, _MAX_PATH) == nullptr) { return false; }
+  resolved = buf;
+#else
+  char buf[PATH_MAX];
+  if (realpath(path, buf) == nullptr) { return false; }
+  resolved = buf;
+#endif
+  return true;
+}
+
+bool is_path_within_base(const std::string &resolved_path,
+                                const std::string &resolved_base) {
+#if defined(_WIN32)
+  return _strnicmp(resolved_path.c_str(), resolved_base.c_str(),
+                   resolved_base.size()) == 0;
+#else
+  return strncmp(resolved_path.c_str(), resolved_base.c_str(),
+                 resolved_base.size()) == 0;
+#endif
+}
+
 FileStat::FileStat(const std::string &path) {
 #if defined(_WIN32)
   auto wpath = u8string_to_wstring(path.c_str());
@@ -2627,33 +2651,114 @@ bool can_compress_content_type(const std::string &content_type) {
   }
 }
 
+bool parse_quality(const char *b, const char *e, std::string &token,
+                          double &quality) {
+  quality = 1.0;
+  token.clear();
+
+  // Split on first ';': left = token name, right = parameters
+  const char *params_b = nullptr;
+  std::size_t params_len = 0;
+
+  divide(
+      b, static_cast<std::size_t>(e - b), ';',
+      [&](const char *lb, std::size_t llen, const char *rb, std::size_t rlen) {
+        auto r = trim(lb, lb + llen, 0, llen);
+        if (r.first < r.second) { token.assign(lb + r.first, lb + r.second); }
+        params_b = rb;
+        params_len = rlen;
+      });
+
+  if (token.empty()) { return false; }
+  if (params_len == 0) { return true; }
+
+  // Scan parameters for q= (stops on first match)
+  bool invalid = false;
+  split_find(params_b, params_b + params_len, ';',
+             (std::numeric_limits<size_t>::max)(),
+             [&](const char *pb, const char *pe) -> bool {
+               // Match exactly "q=" or "Q=" (not "query=" etc.)
+               auto len = static_cast<size_t>(pe - pb);
+               if (len < 2) { return false; }
+               if ((pb[0] != 'q' && pb[0] != 'Q') || pb[1] != '=') {
+                 return false;
+               }
+
+               // Trim the value portion
+               auto r = trim(pb, pe, 2, len);
+               if (r.first >= r.second) {
+                 invalid = true;
+                 return true;
+               }
+
+               double v = 0.0;
+               auto res = from_chars(pb + r.first, pb + r.second, v);
+               if (res.ec != std::errc{} || v < 0.0 || v > 1.0) {
+                 invalid = true;
+                 return true;
+               }
+               quality = v;
+               return true;
+             });
+
+  return !invalid;
+}
+
 EncodingType encoding_type(const Request &req, const Response &res) {
-  auto ret =
-      detail::can_compress_content_type(res.get_header_value("Content-Type"));
-  if (!ret) { return EncodingType::None; }
+  if (!can_compress_content_type(res.get_header_value("Content-Type"))) {
+    return EncodingType::None;
+  }
 
   const auto &s = req.get_header_value("Accept-Encoding");
-  (void)(s);
+  if (s.empty()) { return EncodingType::None; }
 
+  // Single-pass: iterate tokens and track the best supported encoding.
+  // Server preference breaks ties (br > gzip > zstd).
+  EncodingType best = EncodingType::None;
+  double best_q = 0.0; // q=0 means "not acceptable"
+
+  // Server preference: Brotli > Gzip > Zstd (lower = more preferred)
+  auto priority = [](EncodingType t) -> int {
+    switch (t) {
+    case EncodingType::Brotli: return 0;
+    case EncodingType::Gzip: return 1;
+    case EncodingType::Zstd: return 2;
+    default: return 3;
+    }
+  };
+
+  std::string name;
+  split(s.data(), s.data() + s.size(), ',', [&](const char *b, const char *e) {
+    double quality = 1.0;
+    if (!parse_quality(b, e, name, quality)) { return; }
+    if (quality <= 0.0) { return; }
+
+    EncodingType type = EncodingType::None;
 #ifdef CPPHTTPLIB_BROTLI_SUPPORT
-  // TODO: 'Accept-Encoding' has br, not br;q=0
-  ret = s.find("br") != std::string::npos;
-  if (ret) { return EncodingType::Brotli; }
+    if (case_ignore::equal(name, "br")) { type = EncodingType::Brotli; }
 #endif
-
 #ifdef CPPHTTPLIB_ZLIB_SUPPORT
-  // TODO: 'Accept-Encoding' has gzip, not gzip;q=0
-  ret = s.find("gzip") != std::string::npos;
-  if (ret) { return EncodingType::Gzip; }
+    if (type == EncodingType::None && case_ignore::equal(name, "gzip")) {
+      type = EncodingType::Gzip;
+    }
 #endif
-
 #ifdef CPPHTTPLIB_ZSTD_SUPPORT
-  // TODO: 'Accept-Encoding' has zstd, not zstd;q=0
-  ret = s.find("zstd") != std::string::npos;
-  if (ret) { return EncodingType::Zstd; }
+    if (type == EncodingType::None && case_ignore::equal(name, "zstd")) {
+      type = EncodingType::Zstd;
+    }
 #endif
 
-  return EncodingType::None;
+    if (type == EncodingType::None) { return; }
+
+    // Higher q-value wins; for equal q, server preference breaks ties
+    if (quality > best_q ||
+        (quality == best_q && priority(type) < priority(best))) {
+      best_q = quality;
+      best = type;
+    }
+  });
+
+  return best;
 }
 
 bool nocompressor::compress(const char *data, size_t data_length,
@@ -2937,6 +3042,21 @@ create_decompressor(const std::string &encoding) {
   return decompressor;
 }
 
+// Returns the best available compressor and its Content-Encoding name.
+// Priority: Brotli > Gzip > Zstd (matches server-side preference).
+std::pair<std::unique_ptr<compressor>, const char *>
+create_compressor() {
+#ifdef CPPHTTPLIB_BROTLI_SUPPORT
+  return {detail::make_unique<brotli_compressor>(), "br"};
+#elif defined(CPPHTTPLIB_ZLIB_SUPPORT)
+  return {detail::make_unique<gzip_compressor>(), "gzip"};
+#elif defined(CPPHTTPLIB_ZSTD_SUPPORT)
+  return {detail::make_unique<zstd_compressor>(), "zstd"};
+#else
+  return {nullptr, nullptr};
+#endif
+}
+
 bool is_prohibited_header_name(const std::string &name) {
   using udl::operator""_t;
 
@@ -3769,7 +3889,7 @@ bool parse_accept_header(const std::string &s,
   struct AcceptEntry {
     std::string media_type;
     double quality;
-    int order; // Original order in header
+    int order;
   };
 
   std::vector<AcceptEntry> entries;
@@ -3787,48 +3907,12 @@ bool parse_accept_header(const std::string &s,
     }
 
     AcceptEntry accept_entry;
-    accept_entry.quality = 1.0; // Default quality
     accept_entry.order = order++;
 
-    // Find q= parameter
-    auto q_pos = entry.find(";q=");
-    if (q_pos == std::string::npos) { q_pos = entry.find("; q="); }
-
-    if (q_pos != std::string::npos) {
-      // Extract media type (before q parameter)
-      accept_entry.media_type = trim_copy(entry.substr(0, q_pos));
-
-      // Extract quality value
-      auto q_start = entry.find('=', q_pos) + 1;
-      auto q_end = entry.find(';', q_start);
-      if (q_end == std::string::npos) { q_end = entry.length(); }
-
-      std::string quality_str =
-          trim_copy(entry.substr(q_start, q_end - q_start));
-      if (quality_str.empty()) {
-        has_invalid_entry = true;
-        return;
-      }
-
-      {
-        double v = 0.0;
-        auto res = detail::from_chars(
-            quality_str.data(), quality_str.data() + quality_str.size(), v);
-        if (res.ec == std::errc{}) {
-          accept_entry.quality = v;
-        } else {
-          has_invalid_entry = true;
-          return;
-        }
-      }
-      // Check if quality is in valid range [0.0, 1.0]
-      if (accept_entry.quality < 0.0 || accept_entry.quality > 1.0) {
-        has_invalid_entry = true;
-        return;
-      }
-    } else {
-      // No quality parameter, use entire entry as media type
-      accept_entry.media_type = entry;
+    if (!parse_quality(entry.data(), entry.data() + entry.size(),
+                       accept_entry.media_type, accept_entry.quality)) {
+      has_invalid_entry = true;
+      return;
     }
 
     // Remove additional parameters from media type
@@ -5481,7 +5565,8 @@ std::string decode_path_component(const std::string &component) {
         // Unicode %uXXXX encoding
         auto val = 0;
         if (detail::from_hex_to_i(component, i + 2, 4, val)) {
-          // 4 digits Unicode codes
+          // 4 digits Unicode codes: val is 0x0000-0xFFFF (from 4 hex digits),
+          // so to_utf8 writes at most 3 bytes. buff[4] is safe.
           char buff[4];
           size_t len = detail::to_utf8(val, buff);
           if (len > 0) { result.append(buff, len); }
@@ -5586,6 +5671,30 @@ std::string decode_query_component(const std::string &component,
   return result;
 }
 
+std::string sanitize_filename(const std::string &filename) {
+  // Extract basename: find the last path separator (/ or \)
+  auto pos = filename.find_last_of("/\\");
+  auto result =
+      (pos != std::string::npos) ? filename.substr(pos + 1) : filename;
+
+  // Strip null bytes
+  result.erase(std::remove(result.begin(), result.end(), '\0'), result.end());
+
+  // Trim whitespace
+  {
+    auto start = result.find_first_not_of(" \t");
+    auto end = result.find_last_not_of(" \t");
+    result = (start == std::string::npos)
+                 ? ""
+                 : result.substr(start, end - start + 1);
+  }
+
+  // Reject . and ..
+  if (result == "." || result == "..") { return ""; }
+
+  return result;
+}
+
 std::string append_query_params(const std::string &path,
                                        const Params &params) {
   std::string path_with_query = path;
@@ -6714,7 +6823,18 @@ bool Server::set_mount_point(const std::string &mount_point,
   if (stat.is_dir()) {
     std::string mnt = !mount_point.empty() ? mount_point : "/";
     if (!mnt.empty() && mnt[0] == '/') {
-      base_dirs_.push_back({std::move(mnt), dir, std::move(headers)});
+      std::string resolved_base;
+      if (detail::canonicalize_path(dir.c_str(), resolved_base)) {
+#if defined(_WIN32)
+        if (resolved_base.back() != '\\' && resolved_base.back() != '/') {
+          resolved_base += '\\';
+        }
+#else
+        if (resolved_base.back() != '/') { resolved_base += '/'; }
+#endif
+      }
+      base_dirs_.push_back(
+          {std::move(mnt), dir, std::move(resolved_base), std::move(headers)});
       return true;
     }
   }
@@ -6874,6 +6994,20 @@ Server &Server::set_payload_max_length(size_t length) {
   return *this;
 }
 
+Server &Server::set_websocket_ping_interval(time_t sec) {
+  websocket_ping_interval_sec_ = sec;
+  return *this;
+}
+
+template <class Rep, class Period>
+Server &Server::set_websocket_ping_interval(
+    const std::chrono::duration<Rep, Period> &duration) {
+  detail::duration_to_sec_and_usec(duration, [&](time_t sec, time_t /*usec*/) {
+    set_websocket_ping_interval(sec);
+  });
+  return *this;
+}
+
 bool Server::bind_to_port(const std::string &host, int port,
                                  int socket_flags) {
   auto ret = bind_internal(host, port, socket_flags);
@@ -7294,6 +7428,18 @@ bool Server::handle_file_request(Request &req, Response &res) {
         auto path = entry.base_dir + sub_path;
         if (path.back() == '/') { path += "index.html"; }
 
+        // Defense-in-depth: is_valid_path blocks ".." traversal in the URL,
+        // but symlinks/junctions can still escape the base directory.
+        if (!entry.resolved_base_dir.empty()) {
+          std::string resolved_path;
+          if (detail::canonicalize_path(path.c_str(), resolved_path) &&
+              !detail::is_path_within_base(resolved_path,
+                                           entry.resolved_base_dir)) {
+            res.status = StatusCode::Forbidden_403;
+            return true;
+          }
+        }
+
         detail::FileStat stat(path);
 
         if (stat.is_dir()) {
@@ -8012,7 +8158,7 @@ Server::process_request(Stream &strm, const std::string &remote_addr,
         {
           // Use WebSocket-specific read timeout instead of HTTP timeout
           strm.set_read_timeout(CPPHTTPLIB_WEBSOCKET_READ_TIMEOUT_SECOND, 0);
-          ws::WebSocket ws(strm, req, true);
+          ws::WebSocket ws(strm, req, true, websocket_ping_interval_sec_);
           entry.handler(req, ws);
         }
         return true;
@@ -8256,6 +8402,13 @@ bool ClientImpl::ensure_socket_connection(Socket &socket, Error &error) {
   return create_and_connect_socket(socket, error);
 }
 
+bool ClientImpl::setup_proxy_connection(
+    Socket & /*socket*/,
+    std::chrono::time_point<std::chrono::steady_clock> /*start_time*/,
+    Response & /*res*/, bool & /*success*/, Error & /*error*/) {
+  return true;
+}
+
 void ClientImpl::shutdown_ssl(Socket & /*socket*/,
                                      bool /*shutdown_gracefully*/) {
   // If there are any requests in flight from threads other than us, then it's
@@ -8377,27 +8530,14 @@ bool ClientImpl::send_(Request &req, Response &res, Error &error) {
         return false;
       }
 
-#ifdef CPPHTTPLIB_SSL_ENABLED
-      // TODO: refactoring
-      if (is_ssl()) {
-        auto &scli = static_cast<SSLClient &>(*this);
-        if (!proxy_host_.empty() && proxy_port_ != -1) {
-          auto success = false;
-          if (!scli.connect_with_proxy(socket_, req.start_time_, res, success,
-                                       error)) {
-            if (!success) { output_error_log(error, &req); }
-            return success;
-          }
-        }
-
-        if (!proxy_host_.empty() && proxy_port_ != -1) {
-          if (!scli.initialize_ssl(socket_, error)) {
-            output_error_log(error, &req);
-            return false;
-          }
+      {
+        auto success = true;
+        if (!setup_proxy_connection(socket_, req.start_time_, res, success,
+                                    error)) {
+          if (!success) { output_error_log(error, &req); }
+          return success;
         }
       }
-#endif
     }
 
     // Mark the current socket as being in use so that it cannot be closed by
@@ -8558,17 +8698,15 @@ ClientImpl::open_stream(const std::string &method, const std::string &path,
         return handle;
       }
 
-#ifdef CPPHTTPLIB_SSL_ENABLED
-      if (is_ssl()) {
-        auto &scli = static_cast<SSLClient &>(*this);
-        if (!proxy_host_.empty() && proxy_port_ != -1) {
-          if (!scli.initialize_ssl(socket_, handle.error)) {
-            handle.response.reset();
-            return handle;
-          }
+      {
+        auto success = true;
+        auto start_time = std::chrono::steady_clock::now();
+        if (!setup_proxy_connection(socket_, start_time, *handle.response,
+                                    success, handle.error)) {
+          if (!success) { handle.response.reset(); }
+          return handle;
         }
       }
-#endif
     }
 
     transfer_socket_ownership_to_handle(handle);
@@ -8847,7 +8985,7 @@ bool ClientImpl::handle_request(Stream &strm, Request &req,
 
   if (res.get_header_value("Connection") == "close" ||
       (res.version == "HTTP/1.0" && res.reason != "Connection established")) {
-    // TODO this requires a not-entirely-obvious chain of calls to be correct
+    // NOTE: this requires a not-entirely-obvious chain of calls to be correct
     // for this to be safe.
 
     // This is safe to call because handle_request is only called by send_
@@ -9086,14 +9224,9 @@ bool ClientImpl::write_content_with_provider(Stream &strm,
   auto is_shutting_down = []() { return false; };
 
   if (req.is_chunked_content_provider_) {
-    // TODO: Brotli support
-    std::unique_ptr<detail::compressor> compressor;
-#ifdef CPPHTTPLIB_ZLIB_SUPPORT
-    if (compress_) {
-      compressor = detail::make_unique<detail::gzip_compressor>();
-    } else
-#endif
-    {
+    auto compressor = compress_ ? detail::create_compressor().first
+                                : std::unique_ptr<detail::compressor>();
+    if (!compressor) {
       compressor = detail::make_unique<detail::nocompressor>();
     }
 
@@ -9324,14 +9457,15 @@ ClientImpl::send_with_content_provider_and_receiver(
     Error &error) {
   if (!content_type.empty()) { req.set_header("Content-Type", content_type); }
 
-#ifdef CPPHTTPLIB_ZLIB_SUPPORT
-  if (compress_) { req.set_header("Content-Encoding", "gzip"); }
-#endif
+  auto enc = compress_
+                 ? detail::create_compressor()
+                 : std::pair<std::unique_ptr<detail::compressor>, const char *>(
+                       nullptr, nullptr);
 
-#ifdef CPPHTTPLIB_ZLIB_SUPPORT
-  if (compress_ && !content_provider_without_length) {
-    // TODO: Brotli support
-    detail::gzip_compressor compressor;
+  if (enc.second) { req.set_header("Content-Encoding", enc.second); }
+
+  if (enc.first && !content_provider_without_length) {
+    auto &compressor = enc.first;
 
     if (content_provider) {
       auto ok = true;
@@ -9342,7 +9476,7 @@ ClientImpl::send_with_content_provider_and_receiver(
         if (ok) {
           auto last = offset + data_len == content_length;
 
-          auto ret = compressor.compress(
+          auto ret = compressor->compress(
               data, data_len, last,
               [&](const char *compressed_data, size_t compressed_data_len) {
                 req.body.append(compressed_data, compressed_data_len);
@@ -9366,19 +9500,17 @@ ClientImpl::send_with_content_provider_and_receiver(
         }
       }
     } else {
-      if (!compressor.compress(body, content_length, true,
-                               [&](const char *data, size_t data_len) {
-                                 req.body.append(data, data_len);
-                                 return true;
-                               })) {
+      if (!compressor->compress(body, content_length, true,
+                                [&](const char *data, size_t data_len) {
+                                  req.body.append(data, data_len);
+                                  return true;
+                                })) {
         error = Error::Compression;
         output_error_log(error, &req);
         return nullptr;
       }
     }
-  } else
-#endif
-  {
+  } else {
     if (content_provider) {
       req.content_length_ = content_length;
       req.content_provider_ = std::move(content_provider);
@@ -11545,6 +11677,24 @@ bool SSLClient::create_and_connect_socket(Socket &socket, Error &error) {
   return ClientImpl::create_and_connect_socket(socket, error);
 }
 
+bool SSLClient::setup_proxy_connection(
+    Socket &socket,
+    std::chrono::time_point<std::chrono::steady_clock> start_time,
+    Response &res, bool &success, Error &error) {
+  if (proxy_host_.empty() || proxy_port_ == -1) { return true; }
+
+  if (!connect_with_proxy(socket, start_time, res, success, error)) {
+    return false;
+  }
+
+  if (!initialize_ssl(socket, error)) {
+    success = false;
+    return false;
+  }
+
+  return true;
+}
+
 // Assumes that socket_mutex_ is locked and that there are no requests in
 // flight
 bool SSLClient::connect_with_proxy(
@@ -16061,11 +16211,11 @@ WebSocket::~WebSocket() {
 }
 
 void WebSocket::start_heartbeat() {
+  if (ping_interval_sec_ == 0) { return; }
   ping_thread_ = std::thread([this]() {
     std::unique_lock<std::mutex> lock(ping_mutex_);
     while (!closed_) {
-      ping_cv_.wait_for(lock, std::chrono::seconds(
-                                  CPPHTTPLIB_WEBSOCKET_PING_INTERVAL_SECOND));
+      ping_cv_.wait_for(lock, std::chrono::seconds(ping_interval_sec_));
       if (closed_) { break; }
       lock.unlock();
       if (!send_frame(Opcode::Ping, nullptr, 0)) {
@@ -16203,7 +16353,8 @@ bool WebSocketClient::connect() {
   Request req;
   req.method = "GET";
   req.path = path_;
-  ws_ = std::unique_ptr<WebSocket>(new WebSocket(std::move(strm), req, false));
+  ws_ = std::unique_ptr<WebSocket>(
+      new WebSocket(std::move(strm), req, false, websocket_ping_interval_sec_));
   return true;
 }
 
@@ -16243,6 +16394,10 @@ void WebSocketClient::set_write_timeout(time_t sec, time_t usec) {
   write_timeout_usec_ = usec;
 }
 
+void WebSocketClient::set_websocket_ping_interval(time_t sec) {
+  websocket_ping_interval_sec_ = sec;
+}
+
 #ifdef CPPHTTPLIB_SSL_ENABLED
 
 void WebSocketClient::set_ca_cert_path(const std::string &path) {
diff --git a/vendor/cpp-httplib/httplib.h b/vendor/cpp-httplib/httplib.h
index cdde8014d9..6ec949ac51 100644
--- a/vendor/cpp-httplib/httplib.h
+++ b/vendor/cpp-httplib/httplib.h
@@ -8,8 +8,8 @@
 #ifndef CPPHTTPLIB_HTTPLIB_H
 #define CPPHTTPLIB_HTTPLIB_H
 
-#define CPPHTTPLIB_VERSION "0.37.2"
-#define CPPHTTPLIB_VERSION_NUM "0x002502"
+#define CPPHTTPLIB_VERSION "0.38.0"
+#define CPPHTTPLIB_VERSION_NUM "0x002600"
 
 #ifdef _WIN32
 #if defined(_WIN32_WINNT) && _WIN32_WINNT < 0x0A00
@@ -1666,6 +1666,11 @@ public:
 
   Server &set_payload_max_length(size_t length);
 
+  Server &set_websocket_ping_interval(time_t sec);
+  template <class Rep, class Period>
+  Server &set_websocket_ping_interval(
+      const std::chrono::duration<Rep, Period> &duration);
+
   bool bind_to_port(const std::string &host, int port, int socket_flags = 0);
   int bind_to_any_port(const std::string &host, int socket_flags = 0);
   bool listen_after_bind();
@@ -1700,6 +1705,8 @@ protected:
   time_t idle_interval_sec_ = CPPHTTPLIB_IDLE_INTERVAL_SECOND;
   time_t idle_interval_usec_ = CPPHTTPLIB_IDLE_INTERVAL_USECOND;
   size_t payload_max_length_ = CPPHTTPLIB_PAYLOAD_MAX_LENGTH;
+  time_t websocket_ping_interval_sec_ =
+      CPPHTTPLIB_WEBSOCKET_PING_INTERVAL_SECOND;
 
 private:
   using Handlers =
@@ -1769,6 +1776,7 @@ private:
   struct MountPointEntry {
     std::string mount_point;
     std::string base_dir;
+    std::string resolved_base_dir;
     Headers headers;
   };
   std::vector<MountPointEntry> base_dirs_;
@@ -2186,6 +2194,10 @@ protected:
 
   virtual bool create_and_connect_socket(Socket &socket, Error &error);
   virtual bool ensure_socket_connection(Socket &socket, Error &error);
+  virtual bool setup_proxy_connection(
+      Socket &socket,
+      std::chrono::time_point<std::chrono::steady_clock> start_time,
+      Response &res, bool &success, Error &error);
 
   // All of:
   //   shutdown_ssl
@@ -2712,6 +2724,10 @@ private:
                  std::function<bool(Stream &strm)> callback) override;
   bool is_ssl() const override;
 
+  bool setup_proxy_connection(
+      Socket &socket,
+      std::chrono::time_point<std::chrono::steady_clock> start_time,
+      Response &res, bool &success, Error &error) override;
   bool connect_with_proxy(
       Socket &sock,
       std::chrono::time_point<std::chrono::steady_clock> start_time,
@@ -2911,6 +2927,8 @@ std::string encode_query_component(const std::string &component,
 std::string decode_query_component(const std::string &component,
                                    bool plus_as_space = true);
 
+std::string sanitize_filename(const std::string &filename);
+
 std::string append_query_params(const std::string &path, const Params &params);
 
 std::pair<std::string, std::string> make_range_header(const Ranges &ranges);
@@ -3714,15 +3732,19 @@ private:
   friend class httplib::Server;
   friend class WebSocketClient;
 
-  WebSocket(Stream &strm, const Request &req, bool is_server)
-      : strm_(strm), req_(req), is_server_(is_server) {
+  WebSocket(
+      Stream &strm, const Request &req, bool is_server,
+      time_t ping_interval_sec = CPPHTTPLIB_WEBSOCKET_PING_INTERVAL_SECOND)
+      : strm_(strm), req_(req), is_server_(is_server),
+        ping_interval_sec_(ping_interval_sec) {
     start_heartbeat();
   }
 
-  WebSocket(std::unique_ptr<Stream> &&owned_strm, const Request &req,
-            bool is_server)
+  WebSocket(
+      std::unique_ptr<Stream> &&owned_strm, const Request &req, bool is_server,
+      time_t ping_interval_sec = CPPHTTPLIB_WEBSOCKET_PING_INTERVAL_SECOND)
       : strm_(*owned_strm), owned_strm_(std::move(owned_strm)), req_(req),
-        is_server_(is_server) {
+        is_server_(is_server), ping_interval_sec_(ping_interval_sec) {
     start_heartbeat();
   }
 
@@ -3733,6 +3755,7 @@ private:
   std::unique_ptr<Stream> owned_strm_;
   Request req_;
   bool is_server_;
+  time_t ping_interval_sec_;
   std::atomic<bool> closed_{false};
   std::mutex write_mutex_;
   std::thread ping_thread_;
@@ -3761,6 +3784,7 @@ public:
   const std::string &subprotocol() const;
   void set_read_timeout(time_t sec, time_t usec = 0);
   void set_write_timeout(time_t sec, time_t usec = 0);
+  void set_websocket_ping_interval(time_t sec);
 
 #ifdef CPPHTTPLIB_SSL_ENABLED
   void set_ca_cert_path(const std::string &path);
@@ -3784,6 +3808,8 @@ private:
   time_t read_timeout_usec_ = 0;
   time_t write_timeout_sec_ = CPPHTTPLIB_CLIENT_WRITE_TIMEOUT_SECOND;
   time_t write_timeout_usec_ = CPPHTTPLIB_CLIENT_WRITE_TIMEOUT_USECOND;
+  time_t websocket_ping_interval_sec_ =
+      CPPHTTPLIB_WEBSOCKET_PING_INTERVAL_SECOND;
 
 #ifdef CPPHTTPLIB_SSL_ENABLED
   bool is_ssl_ = false;