runner: Remove CGO engines, use llama-server exclusively for GGML models

Remove the vendored GGML and llama.cpp backend, CGO runner, Go model
implementations, and sample.  llama-server (built from upstream llama.cpp via
FetchContent) is now the sole inference engine for GGUF-based models.
(Safetensor based models continue to run on the new MLX engine.)  This allows
us to more rapidly pick up new capabilities and fixes from llama.cpp as they
come out.

On windows this now requires recent AMD driver versions to support ROCm v7 as
llama.cpp currently does not support building against v6.

.github/workflows/release.yaml

@@ -24,7 +24,7 @@ jobs:
         run: |
           echo GOFLAGS="'-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=${GITHUB_REF_NAME#v}\" \"-X=github.com/ollama/ollama/server.mode=release\"'" | tee -a $GITHUB_OUTPUT
           echo VERSION="${GITHUB_REF_NAME#v}" | tee -a $GITHUB_OUTPUT
-          echo vendorsha=$(make -f Makefile.sync print-base) | tee -a $GITHUB_OUTPUT
+          echo vendorsha=$(cat LLAMA_CPP_VERSION) | tee -a $GITHUB_OUTPUT
 
   darwin-build:
     runs-on: macos-26-xlarge
@@ -57,7 +57,7 @@ jobs:
           go-version-file: go.mod
           cache-dependency-path: |
             go.sum
-            Makefile.sync
+            LLAMA_CPP_VERSION
       - run: |
           ./scripts/build_darwin.sh
       - name: Log build results
@@ -106,10 +106,10 @@ jobs:
             flags: ''
           - os: windows
             arch: amd64
-            preset: 'ROCm 6'
-            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
-            rocm-version: '6.2'
-            flags: '-DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
+            preset: 'ROCm 7'
+            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-26.Q1-Win11-For-HIP.exe
+            rocm-version: '7.1'
+            flags: '-DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
             runner_dir: 'rocm'
           - os: windows
             arch: amd64
@@ -232,14 +232,66 @@ jobs:
         with:
           path: ${{ github.workspace }}\.ccache
           key: ccache-${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.preset }}-${{ needs.setup-environment.outputs.vendorsha }}
-      - name: Build target "${{ matrix.preset }}"
+      - name: Build MLX
+        if: startsWith(matrix.preset, 'MLX ')
         run: |
           Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
           Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
           cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }} --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
-          cmake --build --parallel ([Environment]::ProcessorCount) --preset "${{ matrix.preset }}"
-          cmake --install build --component "${{ startsWith(matrix.preset, 'MLX ') && 'MLX' || startsWith(matrix.preset, 'CUDA ') && 'CUDA' || startsWith(matrix.preset, 'ROCm ') && 'HIP' || startsWith(matrix.preset, 'Vulkan') && 'Vulkan' || 'CPU' }}" --strip
-          Remove-Item -Path dist\lib\ollama\rocm\rocblas\library\*gfx906* -ErrorAction SilentlyContinue
+          cmake --build --preset "${{ matrix.preset }}" -- -l $([Environment]::ProcessorCount)
+          cmake --install build --component MLX --strip
+      - name: Build llama-server
+        if: matrix.preset == 'CPU'
+        run: |
+          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
+          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
+          cmake -S llama\server --preset cpu --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
+          cmake --build build\llama-server-cpu -- -l $([Environment]::ProcessorCount)
+          cmake --install build\llama-server-cpu --component llama-server --strip
+        env:
+          CMAKE_GENERATOR: Ninja
+      - name: Build llama-server (CUDA)
+        if: startsWith(matrix.preset, 'CUDA ')
+        run: |
+          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
+          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
+          $cudaVer = "${{ matrix.preset }}".Replace('CUDA ', '').Replace(' ', '')
+          $preset = "cuda-v$cudaVer"
+          if ($cudaVer -eq "13") { $preset = "cuda-v13-windows" }
+          cmake -S llama\server --preset $preset ${{ matrix.flags }} --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
+          cmake --build "build\llama-server-$preset" -- -l $([Environment]::ProcessorCount)
+          cmake --install "build\llama-server-$preset" --component llama-server --strip
+        env:
+          CMAKE_GENERATOR: Ninja
+      - name: Build llama-server (ROCm)
+        if: startsWith(matrix.preset, 'ROCm ')
+        run: |
+          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
+          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
+          $hipPath = "${{ env.HIP_PATH }}"
+          $env:HIPCXX = "$hipPath\bin\clang++.exe"
+          $env:HIP_PLATFORM = "amd"
+          $env:CMAKE_PREFIX_PATH = "$hipPath"
+          $env:CC = "$hipPath\bin\clang.exe"
+          $env:CXX = "$hipPath\bin\clang++.exe"
+          cmake -S llama\server --preset rocm -G Ninja `
+              -DCMAKE_HIP_FLAGS="-parallel-jobs=4" `
+              -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" `
+              -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" `
+              -DAMDGPU_TARGETS="gfx942;gfx950;gfx1010;gfx1012;gfx1030;gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151;gfx1200;gfx1201;gfx908:xnack-;gfx90a:xnack+;gfx90a:xnack-" `
+              --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
+          cmake --build build\llama-server-rocm -- -l $([Environment]::ProcessorCount)
+          cmake --install build\llama-server-rocm --component llama-server --strip
+        env:
+          CMAKE_GENERATOR: Ninja
+      - name: Build llama-server (Vulkan)
+        if: matrix.preset == 'Vulkan'
+        run: |
+          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
+          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
+          cmake -S llama\server --preset vulkan --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
+          cmake --build build\llama-server-vulkan -- -l $([Environment]::ProcessorCount)
+          cmake --install build\llama-server-vulkan --component llama-server --strip
         env:
           CMAKE_GENERATOR: Ninja
       - name: Log build results
@@ -297,7 +349,7 @@ jobs:
           go-version-file: go.mod
           cache-dependency-path: |
             go.sum
-            Makefile.sync
+            LLAMA_CPP_VERSION
       - name: Verify gcc is actually clang
         run: |
           $ErrorActionPreference='Continue'
@@ -353,7 +405,7 @@ jobs:
           go-version-file: go.mod
           cache-dependency-path: |
             go.sum
-            Makefile.sync
+            LLAMA_CPP_VERSION
       - uses: actions/download-artifact@v4
         with:
           pattern: depends-windows*
@@ -421,6 +473,7 @@ jobs:
             case "$COMPONENT" in
               bin/ollama*)               echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
               lib/ollama/*.so*)          echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
+              lib/ollama/llama-server*|lib/ollama/llama-quantize*)  echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
               lib/ollama/cuda_v*)        echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
               lib/ollama/vulkan*)        echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
               lib/ollama/mlx*)           echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
@@ -439,7 +492,7 @@ jobs:
           done
       - run: |
           for ARCHIVE in dist/${{ matrix.os }}-${{ matrix.arch }}/*.tar.in; do
-            tar c -C dist/${{ matrix.os }}-${{ matrix.arch }} -T $ARCHIVE --owner 0 --group 0 | zstd --ultra -22 -T0 >$(basename ${ARCHIVE//.*/}.tar.zst);
+            tar c -C dist/${{ matrix.os }}-${{ matrix.arch }} -T $ARCHIVE --owner 0 --group 0 | zstd -9 -T0 >$(basename ${ARCHIVE//.*/}.tar.zst);
           done
       - uses: actions/upload-artifact@v4
         with:

.github/workflows/test.yaml

@@ -37,8 +37,8 @@ jobs:
               | xargs python3 -c "import sys; from pathlib import Path; print(any(Path(x).match(glob) for x in sys.argv[1:] for glob in '$*'.split(' ')))"
           }
 
-          echo changed=$(changed 'llama/llama.cpp/**/*' 'ml/backend/ggml/ggml/**/*' '.github/**/*') | tee -a $GITHUB_OUTPUT
-          echo vendorsha=$(make -f Makefile.sync print-base) | tee -a $GITHUB_OUTPUT
+          echo changed=$(changed 'llama/server/**/*' 'LLAMA_CPP_VERSION' '.github/**/*') | tee -a $GITHUB_OUTPUT
+          echo vendorsha=$(cat LLAMA_CPP_VERSION) | tee -a $GITHUB_OUTPUT
 
   linux:
     needs: [changes]
@@ -80,11 +80,9 @@ jobs:
             echo "deb [signed-by=/usr/share/keyrings/lunarg-archive-keyring.gpg]  https://packages.lunarg.com/vulkan/1.4.313 jammy main" | $sudo tee /etc/apt/sources.list.d/lunarg-vulkan-1.4.313-jammy.list > /dev/null
             $sudo apt-get update
           fi
-          $sudo apt-get install -y cmake ccache ${{ matrix.extra-packages }}
-          # MLX requires CMake 3.25+, install from official releases
-          if [ "${{ matrix.preset }}" = "MLX CUDA 13" ]; then
-            curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.31.2/cmake-3.31.2-linux-$(uname -m).tar.gz | $sudo tar xz -C /usr/local --strip-components 1
-          fi
+          $sudo apt-get install -y cmake ccache curl ${{ matrix.extra-packages }}
+          # llama-server requires CMake 3.24+, while Ubuntu 22.04 ships 3.22.
+          curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.31.2/cmake-3.31.2-linux-$(uname -m).tar.gz | $sudo tar xz -C /usr/local --strip-components 1
           # Export VULKAN_SDK if provided by LunarG package (defensive)
           if [ -d "/usr/lib/x86_64-linux-gnu/vulkan" ] && [ "${{ matrix.preset }}" = "Vulkan" ]; then
             echo "VULKAN_SDK=/usr" >> $GITHUB_ENV
@@ -101,9 +99,10 @@ jobs:
         with:
           path: /github/home/.cache/ccache
           key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
-      - run: |
-          cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
-          cmake --build --preset "${{ matrix.preset }}" --parallel
+      - name: Build llama-server
+        run: |
+          cmake -S llama/server --preset cpu ${{ matrix.flags }}
+          cmake --build build/llama-server-cpu -- -l $(nproc)
 
   windows:
     needs: [changes]
@@ -125,7 +124,8 @@ jobs:
               - '"nvptxcompiler"'
             cuda-version: '13.0'
           - preset: ROCm
-            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
+            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-26.Q1-Win11-For-HIP.exe
+            rocm-version: '7.1'
             flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
           - preset: Vulkan
             install: https://sdk.lunarg.com/sdk/download/1.4.321.1/windows/vulkansdk-windows-X64-1.4.321.1.exe
@@ -234,11 +234,22 @@ jobs:
         with:
           path: ${{ github.workspace }}\.ccache
           key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
-      - run: |
+      - name: Build llama-server
+        if: matrix.preset != 'MLX CUDA 13'
+        run: |
+          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
+          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
+          cmake -S llama\server --preset cpu ${{ matrix.flags }}
+          cmake --build build\llama-server-cpu -- -l $([Environment]::ProcessorCount)
+        env:
+          CMAKE_GENERATOR: Ninja
+      - name: Build MLX
+        if: matrix.preset == 'MLX CUDA 13'
+        run: |
           Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
           Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
           cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
-          cmake --build --parallel --preset "${{ matrix.preset }}"
+          cmake --build --preset "${{ matrix.preset }}" -- -l $([Environment]::ProcessorCount)
         env:
           CMAKE_GENERATOR: Ninja
 
@@ -263,7 +274,7 @@ jobs:
           go-version-file: 'go.mod'
           cache-dependency-path: |
             go.sum
-            Makefile.sync
+            LLAMA_CPP_VERSION
       - uses: actions/setup-node@v4
         with:
           node-version: '20'
@@ -287,12 +298,3 @@ jobs:
       - uses: golangci/golangci-lint-action@v9
         with:
           only-new-issues: true
-
-  patches:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Verify patches apply cleanly and do not change files
-        run: |
-          make -f Makefile.sync clean checkout apply-patches sync
-          git diff --compact-summary --exit-code