Skip to content

Build Release (CUDA) #15

Build Release (CUDA)

Build Release (CUDA) #15

name: Build Release (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
##"12.2.2", "12.3.2", "12.4.1", "12.5.0" "12.2.0" #12.2.0 (prev tag) cuda
steps:
- name: Define Job Output
id: set-matrix
run: |
$matrix = @{
'os' = @('ubuntu-latest')
'pyver' = @("3.12")
'cuda' = @("12.6.2")
'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:
- 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/[email protected]
with:
activate-environment: "llamacpp"
python-version: ${{ matrix.pyver }}
miniforge-version: latest
add-pip-as-python-dependency: true
auto-activate-base: false
- 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
working-directory: vendor/llama-cpp-python
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 -DLLAVA_BUILD=off -DCMAKE_CUDA_ARCHITECTURES=all'
$env:CMAKE_ARGS = "-DGGML_CUDA_FORCE_MMQ=OFF $env:CMAKE_ARGS"
# if ($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: vendor/llama-cpp-python/dist/*
# Set tag_name to <tag>-cu<cuda_version>
tag_name: ${{ github.ref_name }}-cu${{ env.CUDA_VERSION }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}