feat: Update workflows and pre-built wheels (#1416)

* Update build-wheels-cuda.yaml

* Update build-wheels-cuda.yaml

* revert

* Bump pyhton from 3.8 to 3.9

* Remove python 3.8

* Remove Python 3.7 and 3.8 deprecated

* Bump python from 3.8 to 3.9

* Add python 3.9

* Add python 3.9, remove macos-11 deprecated, add macos-14

* Bump python 3.8 to 3.9

* Add python 3.13

* Add python 3.13

* python 3.13 remove

* remove python 3.13

* remove python 3.8

* Bump macos-13 to macos-14

* Update build-wheels-metal.yaml

* Update build-wheels-metal.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-wheels-metal.yaml

* Update generate-index-from-release.yaml

Add avx, avx2 and avx512

* Update test.yaml

* Update test-pypi.yaml

* Update publish.yaml

* Update publish-to-test.yaml

* Update build-wheels-cuda.yaml

Cuda with AVX2 by default

* Update build-wheels-cuda.yaml

* remove DEPRECATED 32 bits

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

Upgrade matrix os to latest version

* Update build-wheels-metal.yaml

* Update build-wheels-cuda.yaml

* Update test.yaml

* Update test-pypi.yaml

* Update test.yaml

Add cache: 'pip'

* Update publish-to-test.yaml

* Update build-wheels-metal.yaml

Add cache: 'pip'

* Update build-wheels-cuda.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-wheels-metal.yaml

remove x86_64

* Update build-wheels-metal.yaml

* Update build-and-release.yaml

* Update build-wheels-metal.yaml

* Update build-wheels-metal.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-wheels-metal.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-and-release.yaml

* Update build-wheels-metal.yaml

* revert

* Remove cpu variants

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>

.github/workflows/build-wheels-cuda.yaml

@@ -20,8 +20,8 @@ jobs:
         id: set-matrix
         run: |
           $matrix = @{
-              'os' = @('ubuntu-20.04', 'windows-latest')
+              'os' = @('ubuntu-latest', 'windows-latest')
-              'pyver' = @("3.10", "3.11", "3.12")
+              'pyver' = @("3.9", "3.10", "3.11", "3.12")
               'cuda' = @("12.1.1", "12.2.2", "12.3.2", "12.4.1")
               'releasetag' = @("basic")
           }
@@ -50,6 +50,7 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.pyver }}
+          cache: 'pip'
 
       - name: Setup Mamba
         uses: conda-incubator/setup-miniconda@v3.0.4
@@ -109,15 +110,15 @@ jobs:
           $env:VERBOSE = '1'
           $env:CMAKE_ARGS = '-DLLAMA_CUBLAS=on -DCMAKE_CUDA_ARCHITECTURES=all'
           $env:CMAKE_ARGS = "-DLLAMA_CUDA_FORCE_MMQ=ON $env:CMAKE_ARGS"
-          if ($env:AVXVER -eq 'AVX') {
+          # if ($env:AVXVER -eq 'AVX') {
-            $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off'
+          $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off'
-          }
+          # }
-          if ($env:AVXVER -eq 'AVX512') {
+          # if ($env:AVXVER -eq 'AVX512') {
-            $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX512=on'
+          #  $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX512=on'
-          }
+          # }
-          if ($env:AVXVER -eq 'basic') {
+          # if ($env:AVXVER -eq 'basic') {
-            $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off'
+          #  $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off'
-          }
+          # }
           python -m build --wheel
           # write the build tag to the output
           Write-Output "CUDA_VERSION=$cudaVersion" >> $env:GITHUB_ENV

.github/workflows/build-wheels-metal.yaml

@@ -6,81 +6,60 @@ permissions:
   contents: write
 
 jobs:
-  define_matrix:
-    name: Define Build Matrix
-    runs-on: ubuntu-latest
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
-    defaults:
-      run:
-        shell: pwsh
-
-    steps:
-      - name: Define Job Output
-        id: set-matrix
-        run: |
-          $matrix = @{
-              'os' = @('macos-11', 'macos-12', 'macos-13')
-              'pyver' = @('3.10', '3.11', '3.12')
-          }
-
-          $matrixOut = ConvertTo-Json $matrix -Compress
-          Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
-
   build_wheels:
-    name: ${{ matrix.os }} Python ${{ matrix.pyver }}
+    name: Build wheels on ${{ matrix.os }}
-    needs: define_matrix
     runs-on: ${{ matrix.os }}
     strategy:
-      matrix: ${{ fromJSON(needs.define_matrix.outputs.matrix) }}
+      matrix:
-    env:
+        os: [macos-12, macos-13, macos-14]
-      OSVER: ${{ matrix.os }}
 
     steps:
       - uses: actions/checkout@v4
         with:
           submodules: "recursive"
 
+      # Used to host cibuildwheel
       - uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.pyver }}
+          python-version: "3.12"
+          cache: 'pip'
 
-      - name: Install Dependencies
+      - name: Install dependencies
         run: |
-          python -m pip install build wheel cmake
+          python -m pip install --upgrade pip
+          python -m pip install -e .[all]
 
-      - name: Build Wheel
+      - name: Build wheels
-        run: |
+        uses: pypa/cibuildwheel@v2.18.1
-          XCODE15PATH="/Applications/Xcode_15.0.app/Contents/Developer"
+        env:
-          XCODE15BINPATH="${XCODE15PATH}/Toolchains/XcodeDefault.xctoolchain/usr/bin"
+          # disable repair
-          export CMAKE_ARGS="-DLLAMA_NATIVE=off -DLLAMA_METAL=on"
+          CIBW_REPAIR_WHEEL_COMMAND: ""
-          [[ "$OSVER" == "macos-13" ]] && export CC="${XCODE15BINPATH}/cc" && export CXX="${XCODE15BINPATH}/c++" && export MACOSX_DEPLOYMENT_TARGET="13.0"
+          CIBW_ARCHS: "arm64"
-          [[ "$OSVER" == "macos-12" ]] && export MACOSX_DEPLOYMENT_TARGET="12.0"
+          CIBW_ENVIRONMENT: CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DLLAMA_METAL=on"
-          [[ "$OSVER" == "macos-11" ]] && export MACOSX_DEPLOYMENT_TARGET="11.0"
+          CIBW_BUILD: "cp39-* cp310-* cp311-* cp312-*"
+        with:
+          package-dir: .
+          output-dir: wheelhouse2
 
-          export CMAKE_OSX_ARCHITECTURES="arm64" && export ARCHFLAGS="-arch arm64"
+      - uses: actions/upload-artifact@v4
-          VERBOSE=1 python -m build --wheel
+        with:
+          name: wheels-mac_${{ matrix.os }}
+          path: ./wheelhouse2/*.whl
 
-          if [[ "$OSVER" == "macos-13" ]]; then
+  release:
-            export SDKROOT="${XCODE15PATH}/Platforms/MacOSX.platform/Developer/SDKs/MacOSX14.0.sdk"
+    name: Release
-            export MACOSX_DEPLOYMENT_TARGET="14.0"
+    needs: [build_wheels]
-            VERBOSE=1 python -m build --wheel
+    runs-on: ubuntu-latest
-          fi
-
-          for file in ./dist/*.whl; do cp "$file" "${file/arm64.whl/aarch64.whl}"; done
-
-          export CMAKE_OSX_ARCHITECTURES="x86_64" && export CMAKE_ARGS="-DLLAMA_NATIVE=off -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_METAL=on" && export ARCHFLAGS="-arch x86_64"
-          VERBOSE=1 python -m build --wheel
-
-          if [[ "$OSVER" == "macos-13" ]]; then
-            export SDKROOT="${XCODE15PATH}/Platforms/MacOSX.platform/Developer/SDKs/MacOSX14.0.sdk"
-            export MACOSX_DEPLOYMENT_TARGET="14.0"
-            VERBOSE=1 python -m build --wheel
-          fi
 
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          merge-multiple: true
+          path: dist2
+          
       - uses: softprops/action-gh-release@v2
         with:
-          files: dist/*
+          files: dist2/*
           # set release name to <tag>-metal
           tag_name: ${{ github.ref_name }}-metal
         env:

.github/workflows/publish-to-test.yaml

@@ -22,7 +22,8 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.8"
+        python-version: "3.11"
+        cache: 'pip'
     - name: Append Dev Version to __version__
       run: |
         DEV_VERSION=${{ github.event.inputs.dev_version }}
@@ -31,11 +32,11 @@ jobs:
         sed -i 's/__version__ = \".*\"/__version__ = \"'"${NEW_VERSION}"'\"/' llama_cpp/__init__.py
     - name: Install dependencies
       run: |
-        python3 -m pip install --upgrade pip build
+        python -m pip install --upgrade pip build
-        python3 -m pip install -e .[all]
+        python -m pip install -e .[all]
     - name: Build source distribution
       run: |
-        python3 -m build --sdist
+        python -m build --sdist
     - name: Publish to Test PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:

.github/workflows/publish.yaml

@@ -16,14 +16,14 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.8"
+        python-version: "3.9"
     - name: Install dependencies
       run: |
-        python3 -m pip install --upgrade pip build
+        python -m pip install --upgrade pip build
-        python3 -m pip install -e .[all]
+        python -m pip install -e .[all]
     - name: Build source distribution
       run: |
-        python3 -m build --sdist
+        python -m build --sdist
     - name: Publish distribution to PyPI
       # TODO: move to tag based releases
       # if: startsWith(github.ref, 'refs/tags')

.github/workflows/test-pypi.yaml

@@ -8,57 +8,60 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install --verbose llama-cpp-python[all]
+          python -m pip install --verbose llama-cpp-python[all]
       - name: Test with pytest
         run: |
-          python3 -c "import llama_cpp"
+          python -c "import llama_cpp"
 
   build-windows:
 
     runs-on: windows-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install --verbose llama-cpp-python[all]
+          python -m pip install --verbose llama-cpp-python[all]
       - name: Test with pytest
         run: |
-          python3 -c "import llama_cpp"
+          python -c "import llama_cpp"
 
   build-macos:
 
     runs-on: macos-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install --verbose llama-cpp-python[all]
+          python -m pip install --verbose llama-cpp-python[all]
       - name: Test with pytest
         run: |
-          python3 -c "import llama_cpp"
+          python -c "import llama_cpp"

.github/workflows/test.yaml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - uses: actions/checkout@v4
@@ -24,20 +24,21 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install .[all] -v
+          python -m pip install .[all] -v
       - name: Test with pytest
         run: |
-          python3 -m pytest
+          python -m pytest
 
   build-windows:
 
     runs-on: windows-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - uses: actions/checkout@v4
@@ -47,20 +48,21 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install .[all] -v
+          python -m pip install .[all] -v
       - name: Test with pytest
         run: |
-          python3 -m pytest
+          python -m pytest
 
   build-macos:
 
-    runs-on: macos-13
+    runs-on: macos-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
       - uses: actions/checkout@v4
@@ -70,13 +72,14 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          python3 -m pip install .[all] --verbose
+          python -m pip install .[all] --verbose
       - name: Test with pytest
         run: |
-          python3 -m pytest
+          python -m pytest
 
   # build-linux-opencl:
 
@@ -98,29 +101,29 @@ jobs:
   #         sudo apt-get install -y --no-install-recommends llvm intel-oneapi-runtime-opencl intel-oneapi-runtime-compilers libclblast-dev
   #     - name: Install dependencies
   #       run: |
-  #         python3 -m pip install --upgrade pip
+  #         python -m pip install --upgrade pip
-  #         CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install .[all] --verbose
+  #         CMAKE_ARGS="-DLLAMA_CLBLAST=on" python -m pip install .[all] --verbose
   #     - name: Test with pytest
   #       run: |
-  #         python3 -m pytest
+  #         python -m pytest
 
 
   build-macos-metal:
 
-    runs-on: macos-13
+    runs-on: macos-latest
 
     steps:
       - uses: actions/checkout@v4
         with:
           submodules: "recursive"
-      - name: Set up Python 3.8
+      - name: Set up Python 3.9
         uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
+          python-version: "3.9"
       - name: Install dependencies
         run: |
-          python3 -m pip install --upgrade pip
+          python -m pip install --upgrade pip
-          CMAKE_ARGS="-DLLAMA_METAL=on" python3 -m pip install .[all] --verbose
+          CMAKE_ARGS="-DLLAMA_METAL=on" python -m pip install .[all] --verbose
       - name: Test with pytest
         run: |
-          python3 -m pytest
+          python -m pytest