name: CI (CUDA, windows)
# TODO: this workflow is only triggered manually because it is very heavy on the CI
# when we provision dedicated windows runners, we can enable it for pushes too
# note: running this workflow manually will populate the ccache for the release builds
# this can be used before merging a PR to speed up the release workflow
on:
workflow_dispatch: # allows manual triggering
# note: this will run in queue with the release workflow
concurrency:
group: release
queue: max
env:
GH_TOKEN: ${{ github.token }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cuda:
name: windows-cuda (${{ matrix.cuda }}, ${{ matrix.arch }})
runs-on: windows-2022
permissions:
actions: write
strategy:
matrix:
include:
- cuda: '12.4'
arch: x64
defines: '-DGGML_CUDA_CUB_3DOT2=ON'
- cuda: '13.3'
arch: x64
defines: ''
- cuda: '13.4'
arch: arm64
defines: '-DCMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-msvc-cuda.cmake'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-windows-2022-${{ matrix.arch }}-cuda-${{ matrix.cuda }}
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
with:
cuda_version: ${{ matrix.cuda }}
cuda_arch: ${{ matrix.arch }}
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
shell: cmd
run: |
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" ${{ matrix.arch == 'x64' && 'x64' || 'amd64_arm64' }}
cmake -S . -B build -G "Ninja Multi-Config" ^
-DGGML_BACKEND_DL=ON ^
-DGGML_NATIVE=OFF ^
-DGGML_CPU=OFF ^
-DGGML_CUDA=ON ^
-DLLAMA_BUILD_BORINGSSL=ON ${{ matrix.defines }}
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% --target ggml-cuda
- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
key: release-windows-2022-${{ matrix.arch }}-cuda-${{ matrix.cuda }}
hip:
runs-on: windows-2022
permissions:
actions: write
env:
# Make sure this is in sync with build-cache.yml
ROCM_VERSION: "7.14.0"
strategy:
matrix:
include:
# sync with release.yml
- name: "radeon"
gpu_targets: "gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# - name: Cache ROCm Installation
# uses: actions/cache@v5
# id: cache-rocm
# with:
# path: C:\TheRock\build
# key: rocm-wheels-${{ env.ROCM_VERSION }}-multi-arch-${{ runner.os }}
- name: Setup ROCm
# if: steps.cache-rocm.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-rocm
with:
version: ${{ env.ROCM_VERSION }}
- name: Setup ROCm Environment
run: |
$ErrorActionPreference = "Stop"
# Activate venv from cache or fresh install
& C:\TheRock\build\.venv\Scripts\Activate.ps1
# Expand the devel tree (idempotent; no-op if already done during install)
rocm-sdk init
if ($LASTEXITCODE -ne 0) { throw "rocm-sdk init failed with exit code $LASTEXITCODE" }
# Get ROCm installation paths using the rocm-sdk CLI tool
$rocmPath = (rocm-sdk path --root)
if (-not $rocmPath) { throw "rocm-sdk path --root returned empty - devel package may not be installed" }
$rocmPath = $rocmPath.Trim()
$cmakePath = (rocm-sdk path --cmake).Trim()
$binPath = (rocm-sdk path --bin).Trim()
write-host "ROCm root: $rocmPath"
echo "HIP_PATH=$rocmPath" >> $env:GITHUB_ENV
echo "CMAKE_PREFIX_PATH=$cmakePath" >> $env:GITHUB_ENV
echo "HIP_DEVICE_LIB_PATH=$rocmPath\lib\llvm\amdgcn\bitcode" >> $env:GITHUB_ENV
echo "HIP_PLATFORM=amd" >> $env:GITHUB_ENV
echo "LLVM_PATH=$rocmPath\lib\llvm" >> $env:GITHUB_ENV
echo "$binPath" >> $env:GITHUB_PATH
# Keep venv in PATH for subsequent steps
echo "C:\TheRock\build\.venv\Scripts" >> $env:GITHUB_PATH
- name: Verify ROCm
id: verify
run: |
# Test the ROCm clang shipped in the installed wheel
& "${env:HIP_PATH}\lib\llvm\bin\clang.exe" --version
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
# TODO: this build does not match the build in release.yml, so we use a different cache key
# ideally, the builds should match, similar to the CUDA build above so that we would be able
# to populate the ccache for the release with manual runs of this workflow
#key: release-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
- name: Build
id: cmake_build
run: |
cmake -G "Unix Makefiles" -B build -S . `
-DCMAKE_PREFIX_PATH="${env:HIP_PATH}" `
-DCMAKE_C_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DCMAKE_CXX_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang++.exe" `
-DCMAKE_HIP_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DCMAKE_BUILD_TYPE=Release `
-DLLAMA_BUILD_BORINGSSL=ON `
-DHIP_PATH="${env:HIP_PATH}" `
-DGGML_HIP=ON `
-DGPU_TARGETS="gfx1100" `
-DGGML_RPC=ON
cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
#key: release-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}