llama-cpp-python 0.2.79__tar.gz → 0.2.81__tar.gz

llama_cpp_python-0.2.81/.git/FETCH_HEAD

@@ -0,0 +1 @@
+01bddd669ca1208f1844ce8d0ba9872532641c9d		'01bddd669ca1208f1844ce8d0ba9872532641c9d' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.2.81/.git/HEAD

@@ -0,0 +1 @@
+01bddd669ca1208f1844ce8d0ba9872532641c9d

llama_cpp_python-0.2.81/.git/config

@@ -0,0 +1,15 @@
+[core]
+	repositoryformatversion = 0
+	filemode = true
+	bare = false
+	logallrefupdates = true
+[remote "origin"]
+	url = https://github.com/abetlen/llama-cpp-python
+	fetch = +refs/heads/*:refs/remotes/origin/*
+[gc]
+	auto = 0
+[http "https://github.com/"]
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX3NQR1RseE1NMTh2UElUT25MSDhMQjlUNnBkMEZieTI3UG5KZw==
+[submodule "vendor/llama.cpp"]
+	active = true
+	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.81/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 01bddd669ca1208f1844ce8d0ba9872532641c9d runner <runner@fv-az651-306.(none)> 1719936227 +0000	checkout: moving from master to refs/tags/v0.2.81

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+968967376dc2c018d29f897c4883d335bbf384fb

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/config

@@ -0,0 +1,22 @@
+[core]
+	repositoryformatversion = 0
+	filemode = true
+	bare = false
+	logallrefupdates = true
+	worktree = ../../../../vendor/llama.cpp
+[remote "origin"]
+	url = https://github.com/ggerganov/llama.cpp.git
+	fetch = +refs/heads/master:refs/remotes/origin/master
+[branch "master"]
+	remote = origin
+	merge = refs/heads/master
+[submodule "kompute"]
+	active = true
+	url = https://github.com/nomic-ai/kompute.git
+[gc]
+	auto = 0
+[http "https://github.com/"]
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX3NQR1RseE1NMTh2UElUT25MSDhMQjlUNnBkMEZieTI3UG5KZw==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 968967376dc2c018d29f897c4883d335bbf384fb runner <runner@fv-az651-306.(none)> 1719936228 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+968967376dc2c018d29f897c4883d335bbf384fb 968967376dc2c018d29f897c4883d335bbf384fb runner <runner@fv-az651-306.(none)> 1719936229 +0000	checkout: moving from master to 968967376dc2c018d29f897c4883d335bbf384fb

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 968967376dc2c018d29f897c4883d335bbf384fb runner <runner@fv-az651-306.(none)> 1719936228 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 968967376dc2c018d29f897c4883d335bbf384fb runner <runner@fv-az651-306.(none)> 1719936228 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/modules/kompute/config

@@ -0,0 +1,19 @@
+[core]
+	repositoryformatversion = 0
+	filemode = true
+	bare = false
+	logallrefupdates = true
+	worktree = ../../../../../../vendor/llama.cpp/ggml/src/kompute
+[remote "origin"]
+	url = https://github.com/nomic-ai/kompute.git
+	fetch = +refs/heads/master:refs/remotes/origin/master
+[branch "master"]
+	remote = origin
+	merge = refs/heads/master
+[gc]
+	auto = 0
+[http "https://github.com/"]
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX3NQR1RseE1NMTh2UElUT25MSDhMQjlUNnBkMEZieTI3UG5KZw==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/modules/kompute/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az651-306.(none)> 1719936229 +0000	clone: from https://github.com/nomic-ai/kompute.git
+c339310f6ff914c5b94fb2353f01a33dfc35f64f 4565194ed7c32d1d2efa32ceab4d3c6cae006306 runner <runner@fv-az651-306.(none)> 1719936230 +0000	checkout: moving from master to 4565194ed7c32d1d2efa32ceab4d3c6cae006306

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az651-306.(none)> 1719936229 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az651-306.(none)> 1719936229 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+968967376dc2c018d29f897c4883d335bbf384fb refs/remotes/origin/master

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+968967376dc2c018d29f897c4883d335bbf384fb

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/refs/tags/b3282

@@ -0,0 +1 @@
+968967376dc2c018d29f897c4883d335bbf384fb

llama_cpp_python-0.2.81/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+968967376dc2c018d29f897c4883d335bbf384fb

llama_cpp_python-0.2.81/.git/refs/tags/v0.2.81

@@ -0,0 +1 @@
+01bddd669ca1208f1844ce8d0ba9872532641c9d

llama_cpp_python-0.2.81/.git/shallow

@@ -0,0 +1 @@
+01bddd669ca1208f1844ce8d0ba9872532641c9d

llama_cpp_python-0.2.81/.github/workflows/build-and-release.yaml

@@ -0,0 +1,112 @@
+name: Build Release
+
+on: workflow_dispatch
+
+permissions:
+  contents: write
+
+jobs:
+  build_wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-20.04, windows-2019, macos-12]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      # Used to host cibuildwheel
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.8"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e .[all]
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.19.1
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
+        with:
+          package-dir: .
+          output-dir: wheelhouse
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: wheels-${{ matrix.os }}
+          path: ./wheelhouse/*.whl
+
+  build_wheels_arm64:
+    name: Build arm64 wheels
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+        with:
+          platforms: linux/arm64
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.19.1
+        env:
+          CIBW_SKIP: "*musllinux* pp*"
+          CIBW_REPAIR_WHEEL_COMMAND: ""
+          CIBW_ARCHS: "aarch64"
+          CIBW_BUILD: "cp38-* cp39-* cp310-* cp311-* cp312-*"
+        with:
+          output-dir: wheelhouse
+
+      - name: Upload wheels as artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels_arm64
+          path: ./wheelhouse/*.whl
+
+  build_sdist:
+    name: Build source distribution
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip build
+          python -m pip install -e .[all]
+      - name: Build source distribution
+        run: |
+          python -m build --sdist
+      - uses: actions/upload-artifact@v4
+        with:
+          name: sdist
+          path: ./dist/*.tar.gz
+
+  release:
+    name: Release
+    needs: [build_wheels, build_wheels_arm64, build_sdist]
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          merge-multiple: true
+          path: dist
+
+      - uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

llama_cpp_python-0.2.81/.github/workflows/build-docker.yaml

@@ -0,0 +1,50 @@
+name: Build Docker
+
+on: workflow_dispatch
+
+permissions:
+  contents: write
+  packages: write
+
+jobs:
+  docker:
+    name: Build and push Docker image
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3 
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push
+        id: docker_build
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: "docker/simple/Dockerfile"
+          push: ${{ startsWith(github.ref, 'refs/tags/') }}
+          pull: true
+          platforms: linux/amd64,linux/arm64
+          tags: |
+            ghcr.io/abetlen/llama-cpp-python:latest
+            ghcr.io/abetlen/llama-cpp-python:${{ github.ref_name }}
+          build-args: |
+            BUILDKIT_INLINE_CACHE=1
+
+      - name: Publish to GitHub Tag
+        if: steps.docker_build.outputs.digest && startsWith(github.ref, 'refs/tags/')
+        run: |
+          echo "Docker image published for tag: ${{ github.ref_name }}"

llama_cpp_python-0.2.81/.github/workflows/build-wheels-cuda.yaml

@@ -0,0 +1,138 @@
+name: Build Wheels (CUDA)
+
+on: workflow_dispatch
+
+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' = @('ubuntu-latest', 'windows-2019')
+              'pyver' = @("3.9", "3.10", "3.11", "3.12")
+              'cuda' = @("12.1.1", "12.2.2", "12.3.2", "12.4.1")
+              'releasetag' = @("basic")
+          }
+
+          $matrixOut = ConvertTo-Json $matrix -Compress
+          Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
+
+  build_wheels:
+    name: Build Wheel ${{ matrix.os }} ${{ matrix.pyver }} ${{ matrix.cuda }} ${{ matrix.releasetag == 'wheels' && 'AVX2' || matrix.releasetag }}
+    needs: define_matrix
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix: ${{ fromJSON(needs.define_matrix.outputs.matrix) }}
+    defaults:
+      run:
+        shell: pwsh
+    env:
+      CUDAVER: ${{ matrix.cuda }}
+      AVXVER: ${{ matrix.releasetag }}
+
+    steps:
+      - name: Add MSBuild to PATH
+        if: runner.os == 'Windows'
+        uses: microsoft/setup-msbuild@v1.1
+        with:
+          vs-version: '[16.11,16.12)'
+
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.pyver }}
+          cache: 'pip'
+
+      - name: Setup Mamba
+        uses: conda-incubator/setup-miniconda@v3.0.4
+        with:
+          activate-environment: "build"
+          python-version: ${{ matrix.pyver }}
+          miniforge-variant: Mambaforge
+          miniforge-version: latest
+          use-mamba: true
+          add-pip-as-python-dependency: true
+          auto-activate-base: false
+
+      - name: VS Integration Cache
+        id: vs-integration-cache
+        if: runner.os == 'Windows'
+        uses: actions/cache@v4.0.2
+        with:
+          path: ./MSBuildExtensions
+          key: cuda-${{ matrix.cuda }}-vs-integration
+
+      - name: Get Visual Studio Integration
+        if: runner.os == 'Windows' && steps.vs-integration-cache.outputs.cache-hit != 'true'
+        run: |
+          if ($env:CUDAVER -eq '12.1.1') {$x = '12.1.0'} else {$x = $env:CUDAVER}
+          $links = (Invoke-RestMethod 'https://raw.githubusercontent.com/Jimver/cuda-toolkit/master/src/links/windows-links.ts').Trim().split().where({$_ -ne ''})
+          for ($i=$q=0;$i -lt $links.count -and $q -lt 2;$i++) {if ($links[$i] -eq "'$x',") {$q++}}
+          Invoke-RestMethod $links[$i].Trim("'") -OutFile 'cudainstaller.zip'
+          & 'C:\Program Files\7-Zip\7z.exe' e cudainstaller.zip -oMSBuildExtensions -r *\MSBuildExtensions\* > $null
+          Remove-Item 'cudainstaller.zip'
+
+      - name: Install Visual Studio Integration
+        if: runner.os == 'Windows'
+        run: |
+          $y = (gi '.\MSBuildExtensions').fullname + '\*'
+          (gi 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\MSBuild\Microsoft\VC\*\BuildCustomizations').fullname.foreach({cp $y $_})
+          $cupath = 'CUDA_PATH_V' + $env:CUDAVER.Remove($env:CUDAVER.LastIndexOf('.')).Replace('.','_')
+          echo "$cupath=$env:CONDA_PREFIX" >> $env:GITHUB_ENV
+
+      - name: Install Dependencies
+        env:
+          MAMBA_DOWNLOAD_FAILFAST: "0"
+          MAMBA_NO_LOW_SPEED_LIMIT: "1"
+        run: |
+          $cudaVersion = $env:CUDAVER
+          mamba install -y 'cuda' -c nvidia/label/cuda-$cudaVersion
+          python -m pip install build wheel
+
+      - name: Build Wheel
+        run: |
+          $cudaVersion = $env:CUDAVER.Remove($env:CUDAVER.LastIndexOf('.')).Replace('.','')
+          $env:CUDA_PATH = $env:CONDA_PREFIX
+          $env:CUDA_HOME = $env:CONDA_PREFIX
+          $env:CUDA_TOOLKIT_ROOT_DIR = $env:CONDA_PREFIX
+          if ($IsLinux) {
+            $env:LD_LIBRARY_PATH = $env:CONDA_PREFIX + '/lib:' + $env:LD_LIBRARY_PATH
+          }
+          $env:VERBOSE = '1'
+          $env:CMAKE_ARGS = '-DLLAMA_CUDA=on -DCMAKE_CUDA_ARCHITECTURES=all'
+          $env:CMAKE_ARGS = "-DLLAMA_CUDA_FORCE_MMQ=ON $env:CMAKE_ARGS"
+          # if ($env:AVXVER -eq 'AVX') {
+          $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX2=off -DLLAMA_FMA=off -DLLAMA_F16C=off'
+          # }
+          # if ($env:AVXVER -eq 'AVX512') {
+          #  $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DLLAMA_AVX512=on'
+          # }
+          # if ($env:AVXVER -eq 'basic') {
+          #  $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
+
+      - uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          # Set tag_name to <tag>-cu<cuda_version>
+          tag_name: ${{ github.ref_name }}-cu${{ env.CUDA_VERSION }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

llama_cpp_python-0.2.81/.github/workflows/build-wheels-metal.yaml

@@ -0,0 +1,66 @@
+name: Build Wheels (Metal)
+
+on: workflow_dispatch
+
+permissions:
+  contents: write
+
+jobs:
+  build_wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-12, macos-13, macos-14]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      # Used to host cibuildwheel
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e .[all]
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.19.1
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
+          CIBW_ARCHS: "arm64"
+          CIBW_ENVIRONMENT: CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DLLAMA_METAL=on"
+          CIBW_BUILD: "cp39-* cp310-* cp311-* cp312-*"
+        with:
+          package-dir: .
+          output-dir: wheelhouse2
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: wheels-mac_${{ matrix.os }}
+          path: ./wheelhouse2/*.whl
+
+  release:
+    name: Release
+    needs: [build_wheels]
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          merge-multiple: true
+          path: dist2
+          
+      - uses: softprops/action-gh-release@v2
+        with:
+          files: dist2/*
+          # set release name to <tag>-metal
+          tag_name: ${{ github.ref_name }}-metal
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

llama_cpp_python-0.2.81/.github/workflows/test.yaml

@@ -0,0 +1,103 @@
+name: Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+
+jobs:
+  build-linux:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[all] -v
+      - name: Test with pytest
+        run: |
+          python -m pytest
+
+  build-windows:
+
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[all] -v
+      - name: Test with pytest
+        run: |
+          python -m pytest
+
+  build-macos:
+
+    runs-on: macos-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[all] --verbose
+      - name: Test with pytest
+        run: |
+          python -m pytest
+
+
+  build-macos-metal:
+
+    runs-on: macos-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          CMAKE_ARGS="-DLLAMA_METAL=on" python -m pip install .[all] --verbose
+      - name: Test with pytest
+        run: |
+          python -m pytest