llama-cpp-python 0.3.6__tar.gz → 0.3.8__tar.gz

llama_cpp_python-0.3.8/.git/FETCH_HEAD

@@ -0,0 +1 @@
+37eb5f0a4c2a8706b89ead1406b1577c4602cdec		'37eb5f0a4c2a8706b89ead1406b1577c4602cdec' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.3.8/.git/HEAD

@@ -0,0 +1 @@
+37eb5f0a4c2a8706b89ead1406b1577c4602cdec

llama_cpp_python-0.3.8/.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 eC1hY2Nlc3MtdG9rZW46Z2hzX3huZmJHUENUQW1BZDk3c0QxU1k2T2lYQXA3UmNtZzRlcGd6Rg==
+[submodule "vendor/llama.cpp"]
+	active = true
+	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.8/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 37eb5f0a4c2a8706b89ead1406b1577c4602cdec runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772529 +0000	checkout: moving from master to refs/tags/v0.3.8

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/FETCH_HEAD

@@ -0,0 +1 @@
+7841fc723e059d1fd9640e5c0ef19050fcc7c698		'7841fc723e059d1fd9640e5c0ef19050fcc7c698' of https://github.com/ggerganov/llama.cpp

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+7841fc723e059d1fd9640e5c0ef19050fcc7c698

llama_cpp_python-0.3.8/.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 eC1hY2Nlc3MtdG9rZW46Z2hzX3huZmJHUENUQW1BZDk3c0QxU1k2T2lYQXA3UmNtZzRlcGd6Rg==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 34c961b181836a4f06ab4c56d5ce61ce03fc478b runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772530 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+34c961b181836a4f06ab4c56d5ce61ce03fc478b 7841fc723e059d1fd9640e5c0ef19050fcc7c698 runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772531 +0000	checkout: moving from master to 7841fc723e059d1fd9640e5c0ef19050fcc7c698

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 34c961b181836a4f06ab4c56d5ce61ce03fc478b runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772530 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 34c961b181836a4f06ab4c56d5ce61ce03fc478b runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772530 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.3.8/.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 eC1hY2Nlc3MtdG9rZW46Z2hzX3huZmJHUENUQW1BZDk3c0QxU1k2T2lYQXA3UmNtZzRlcGd6Rg==
+[url "https://github.com/"]
+	insteadOf = git@github.com:
+	insteadOf = org-6826477@github.com:

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/modules/kompute/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772532 +0000	clone: from https://github.com/nomic-ai/kompute.git
+7c20efa30bb53d08bf04f84e510275766ebe9923 4565194ed7c32d1d2efa32ceab4d3c6cae006306 runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772532 +0000	checkout: moving from master to 4565194ed7c32d1d2efa32ceab4d3c6cae006306

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772532 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 7c20efa30bb53d08bf04f84e510275766ebe9923 runner <runner@fv-az816-766.m0u0gjf3tgau5nacy21rjgffed.cx.internal.cloudapp.net> 1741772532 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+34c961b181836a4f06ab4c56d5ce61ce03fc478b refs/remotes/origin/master

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+34c961b181836a4f06ab4c56d5ce61ce03fc478b

llama_cpp_python-0.3.8/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1,2 @@
+34c961b181836a4f06ab4c56d5ce61ce03fc478b
+7841fc723e059d1fd9640e5c0ef19050fcc7c698

llama_cpp_python-0.3.8/.git/refs/tags/v0.3.8

@@ -0,0 +1 @@
+37eb5f0a4c2a8706b89ead1406b1577c4602cdec

llama_cpp_python-0.3.8/.git/shallow

@@ -0,0 +1 @@
+37eb5f0a4c2a8706b89ead1406b1577c4602cdec

llama_cpp_python-0.3.8/.github/workflows/build-wheels-cuda.yaml

@@ -0,0 +1,136 @@
+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: "llamacpp"
+          python-version: ${{ matrix.pyver }}
+          miniforge-version: latest
+          add-pip-as-python-dependency: true
+          auto-activate-base: false
+
+      - name: VS Integration Cache
+        id: vs-integration-cache
+        if: runner.os == 'Windows'
+        uses: actions/cache@v4
+        with:
+          path: ./MSBuildExtensions
+          key: cuda-${{ 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 }}