llama-cpp-python 0.3.2__tar.gz → 0.3.3__tar.gz

llama_cpp_python-0.3.3/.git/FETCH_HEAD

@@ -0,0 +1 @@
+a9fe0f872527ffc1bf64e125b7996ec4dfa598eb		'a9fe0f872527ffc1bf64e125b7996ec4dfa598eb' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.3.3/.git/HEAD

@@ -0,0 +1 @@
+a9fe0f872527ffc1bf64e125b7996ec4dfa598eb

llama_cpp_python-0.3.3/.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 eC1hY2Nlc3MtdG9rZW46Z2hzXzVPWUlOYkl6RzBpbEU5eE9mU2k0RTN5VExjMVRGdzNPRTIxbQ==
+[submodule "vendor/llama.cpp"]
+	active = true
+	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.3/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 a9fe0f872527ffc1bf64e125b7996ec4dfa598eb runner <runner@fv-az711-799.(none)> 1733717754 +0000	checkout: moving from master to refs/tags/v0.3.3

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171

llama_cpp_python-0.3.3/.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 eC1hY2Nlc3MtdG9rZW46Z2hzXzVPWUlOYkl6RzBpbEU5eE9mU2k0RTN5VExjMVRGdzNPRTIxbQ==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 ce8784bdb153ff7794dde5a50b0ebfa51baa6171 runner <runner@fv-az711-799.(none)> 1733717756 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171 ce8784bdb153ff7794dde5a50b0ebfa51baa6171 runner <runner@fv-az711-799.(none)> 1733717757 +0000	checkout: moving from master to ce8784bdb153ff7794dde5a50b0ebfa51baa6171

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 ce8784bdb153ff7794dde5a50b0ebfa51baa6171 runner <runner@fv-az711-799.(none)> 1733717756 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 ce8784bdb153ff7794dde5a50b0ebfa51baa6171 runner <runner@fv-az711-799.(none)> 1733717756 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.3/.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/ggml-kompute/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 eC1hY2Nlc3MtdG9rZW46Z2hzXzVPWUlOYkl6RzBpbEU5eE9mU2k0RTN5VExjMVRGdzNPRTIxbQ==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/modules/kompute/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az711-799.(none)> 1733717758 +0000	clone: from https://github.com/nomic-ai/kompute.git
+7c20efa30bb53d08bf04f84e510275766ebe9923 4565194ed7c32d1d2efa32ceab4d3c6cae006306 runner <runner@fv-az711-799.(none)> 1733717759 +0000	checkout: moving from master to 4565194ed7c32d1d2efa32ceab4d3c6cae006306

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az711-799.(none)> 1733717758 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az711-799.(none)> 1733717758 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171 refs/remotes/origin/master

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/refs/tags/b4291

@@ -0,0 +1 @@
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171

llama_cpp_python-0.3.3/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+ce8784bdb153ff7794dde5a50b0ebfa51baa6171

llama_cpp_python-0.3.3/.git/refs/tags/v0.3.3

@@ -0,0 +1 @@
+a9fe0f872527ffc1bf64e125b7996ec4dfa598eb

llama_cpp_python-0.3.3/.git/shallow

@@ -0,0 +1 @@
+a9fe0f872527ffc1bf64e125b7996ec4dfa598eb

llama_cpp_python-0.3.3/.github/workflows/build-and-release.yaml

@@ -0,0 +1,144 @@
+name: Build Release
+
+on: workflow_dispatch
+
+permissions:
+  contents: write
+
+jobs:
+  build_wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-20.04, windows-2019, macos-12]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      # Used to host cibuildwheel
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+
+      - name: Install dependencies (Linux/MacOS)
+        if: runner.os != 'Windows'
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
+        shell: bash
+
+      - name: Install dependencies (Windows)
+        if: runner.os == 'Windows'
+        env:
+          RUST_LOG: trace        
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          python -m uv pip install -e .[all] --verbose
+        shell: cmd
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.22.0
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
+        with:
+          package-dir: .
+          output-dir: wheelhouse
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: wheels-${{ 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@v2.22.0
+        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: "3.9"
+
+      - name: Install dependencies (Linux/MacOS)
+        if: runner.os != 'Windows'
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
+          python -m uv pip install build
+        shell: bash
+
+      - name: Install dependencies (Windows)
+        if: runner.os == 'Windows'
+        env:
+          RUST_LOG: trace        
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          python -m uv pip install -e .[all] --verbose
+          python -m uv pip install build
+        shell: cmd
+
+      - 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-0.3.3/.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", "12.5.1", "12.6.1")
+              '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@v2
+        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@v3.1.0
+        with:
+          activate-environment: "build"
+          python-version: ${{ matrix.pyver }}
+          miniforge-variant: Mambaforge
+          miniforge-version: latest
+          use-mamba: true
+          add-pip-as-python-dependency: true
+          auto-activate-base: false
+
+      - name: VS Integration Cache
+        id: vs-integration-cache
+        if: runner.os == 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ./MSBuildExtensions
+          key: cuda-${{ 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 = '-DGGML_CUDA=on -DCMAKE_CUDA_ARCHITECTURES=all'
+          $env:CMAKE_ARGS = "-DGGML_CUDA_FORCE_MMQ=ON $env:CMAKE_ARGS"
+          # if ($env:AVXVER -eq 'AVX') {
+          $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DGGML_AVX2=off -DGGML_FMA=off -DGGML_F16C=off'
+          # }
+          # if ($env:AVXVER -eq 'AVX512') {
+          #  $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DGGML_AVX512=on'
+          # }
+          # if ($env:AVXVER -eq 'basic') {
+          #  $env:CMAKE_ARGS = $env:CMAKE_ARGS + ' -DGGML_AVX=off -DGGML_AVX2=off -DGGML_FMA=off -DGGML_F16C=off'
+          # }
+          python -m build --wheel
+          # write the build tag to the output
+          Write-Output "CUDA_VERSION=$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-0.3.3/.github/workflows/build-wheels-metal.yaml

@@ -0,0 +1,79 @@
+name: Build Wheels (Metal)
+
+on: workflow_dispatch
+
+permissions:
+  contents: write
+
+jobs:
+  build_wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-12, macos-13, macos-14]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      # Used to host cibuildwheel
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+          cache: 'pip'
+          
+      - name: Install dependencies (Linux/MacOS)
+        if: runner.os != 'Windows'
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
+        shell: bash
+
+      - name: Install dependencies (Windows)
+        if: runner.os == 'Windows'
+        env:
+          RUST_LOG: trace        
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          python -m uv pip install -e .[all] --verbose
+        shell: cmd
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.22.0
+        env:
+          # disable repair
+          CIBW_REPAIR_WHEEL_COMMAND: ""
+          CIBW_ARCHS: "arm64"
+          CIBW_ENVIRONMENT: CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DGGML_METAL=on"
+          CIBW_BUILD: "cp39-* cp310-* cp311-* cp312-*"
+        with:
+          package-dir: .
+          output-dir: wheelhouse2
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: wheels-mac_${{ 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-0.3.3/.github/workflows/generate-index-from-release.yaml

@@ -0,0 +1,57 @@
+name: Wheels Index
+
+on:
+  # Trigger on new release
+  workflow_run:
+    workflows: ["Release", "Build Wheels (CUDA)", "Build Wheels (Metal)"]
+    types:
+      - completed
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  # Single deploy job since we're just deploying
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Pages
+        uses: actions/configure-pages@v5
+      - name: Build
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          ./scripts/get-releases.sh
+          ./scripts/releases-to-pep-503.sh index/whl/cpu '^[v]?[0-9]+\.[0-9]+\.[0-9]+$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu121 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu121$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu122 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu122$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu123 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu123$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu124 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu124$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu125 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu124$'
+          ./scripts/releases-to-pep-503.sh index/whl/cu126 '^[v]?[0-9]+\.[0-9]+\.[0-9]+-cu124$'
+          ./scripts/releases-to-pep-503.sh index/whl/metal '^[v]?[0-9]+\.[0-9]+\.[0-9]+-metal$'
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          # Upload entire repository
+          path: 'index'
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4