ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

releases : build CPU backend separately (windows) (#13642)

Browse source
This commit is contained in:
Diego Devesa 2025-05-21 13:09:57 -07:00 • committed by GitHub
parent 8e186ef0e7
commit d643bb2c79
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 142 additions and 125 deletions
Download patch file Download diff file Expand all files Collapse all files

267
.github/workflows/release.yml vendored
View file

@ -1,4 +1,4 @@
name: Create Release
name: Release
on:
workflow_dispatch: # allows manual triggering
@ -227,6 +227,66 @@ jobs:
path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip
name: llama-bin-ubuntu-vulkan-x64.zip
windows-cpu:
runs-on: windows-latest
strategy:
matrix:
include:
- arch: 'x64'
- arch: 'arm64'
steps:
- name: Clone
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: ccache
uses: hendrikmuhs/ccache-action@v1.2.16
with:
key: windows-latest-cmake-cpu-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
- name: Install Ninja
run: |
choco install ninja
- name: libCURL
id: get_libcurl
uses: ./.github/actions/windows-setup-curl
with:
architecture: ${{ matrix.arch == 'x64' && 'win64' || 'win64a' }}
- name: Build
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
cmake -S . -B build -G "Ninja Multi-Config" `
-D CMAKE_TOOLCHAIN_FILE=cmake/${{ matrix.arch }}-windows-llvm.cmake `
-DGGML_NATIVE=OFF `
-DGGML_BACKEND_DL=ON `
-DGGML_CPU_ALL_VARIANTS=ON `
-DGGML_OPENMP=OFF `
-DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" `
${{ env.CMAKE_ARGS }}
cmake --build build --config Release
- name: Pack artifacts
id: pack_artifacts
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
Copy-Item $env:CURL_PATH\bin\libcurl-${{ matrix.arch }}.dll .\build\bin\Release\
7z a llama-bin-win-cpu-${{ matrix.arch }}.zip .\build\bin\Release\*
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: llama-bin-win-cpu-${{ matrix.arch }}.zip
name: llama-bin-win-cpu-${{ matrix.arch }}.zip
windows:
runs-on: windows-latest
@ -237,52 +297,30 @@ jobs:
strategy:
matrix:
include:
- build: 'cpu-x64'
- backend: 'vulkan'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF'
#- build: 'openblas-x64'
# arch: 'x64'
# defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
- build: 'vulkan-x64'
arch: 'x64'
defines: '-DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
- build: 'cpu-arm64'
arch: 'arm64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF'
- build: 'opencl-adreno-arm64'
defines: '-DGGML_VULKAN=ON'
target: 'ggml-vulkan'
- backend: 'opencl-adreno'
arch: 'arm64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON'
target: 'ggml-opencl'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: ccache
uses: hendrikmuhs/ccache-action@v1.2.16
with:
key: windows-latest-cmake-${{ matrix.build }}
key: windows-latest-cmake-${{ matrix.backend }}-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
- name: Download OpenBLAS
id: get_openblas
if: ${{ matrix.build == 'openblas-x64' }}
run: |
curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
mkdir $env:RUNNER_TEMP/openblas
tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas
$vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
$msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
$lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
& $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll
- name: Install Vulkan SDK
id: get_vulkan
if: ${{ matrix.build == 'vulkan-x64' }}
if: ${{ matrix.backend == 'vulkan' }}
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
@ -296,7 +334,7 @@ jobs:
- name: Install OpenCL Headers and Libs
id: install_opencl
if: ${{ matrix.build == 'opencl-adreno-arm64' }}
if: ${{ matrix.backend == 'opencl-adreno' && matrix.arch == 'arm64' }}
run: |
git clone https://github.com/KhronosGroup/OpenCL-Headers
cd OpenCL-Headers
@ -314,46 +352,22 @@ jobs:
-DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
cmake --build build-arm64-release --target install --config release
- name: libCURL
id: get_libcurl
uses: ./.github/actions/windows-setup-curl
with:
architecture: ${{ matrix.arch == 'x64' && 'win64' || 'win64a' }}
- name: Build
id: cmake_build
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
cmake -S . -B build ${{ matrix.defines }} `
-DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" `
${{ env.CMAKE_ARGS }}
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Add libopenblas.dll
id: add_libopenblas_dll
if: ${{ matrix.build == 'openblas-x64' }}
run: |
cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
cmake -S . -B build ${{ matrix.defines }} -DGGML_NATIVE=OFF -DGGML_CPU=OFF -DGGML_BACKEND_DL=ON -DLLAMA_CURL=OFF
cmake --build build --config Release --target ${{ matrix.target }}
- name: Pack artifacts
id: pack_artifacts
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
Copy-Item $env:CURL_PATH\bin\libcurl-${{ matrix.arch }}.dll .\build\bin\Release\
7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip .\build\bin\Release\*
7z a llama-bin-win-${{ matrix.backend }}-${{ matrix.arch }}.zip .\build\bin\Release\${{ matrix.target }}.dll
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip
name: llama-bin-win-${{ matrix.build }}.zip
path: llama-bin-win-${{ matrix.backend }}-${{ matrix.arch }}.zip
name: llama-bin-win-${{ matrix.backend }}-${{ matrix.arch }}.zip
windows-cuda:
runs-on: windows-2019
@ -366,8 +380,6 @@ jobs:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Install ccache
uses: hendrikmuhs/ccache-action@v1.2.16
@ -386,45 +398,30 @@ jobs:
run: |
choco install ninja
- name: libCURL
id: get_libcurl
uses: ./.github/actions/windows-setup-curl
- name: Build
id: cmake_build
shell: cmd
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
cmake -S . -B build -G "Ninja Multi-Config" ^
-DGGML_NATIVE=OFF ^
-DGGML_BACKEND_DL=ON ^
-DGGML_CPU_ALL_VARIANTS=ON ^
-DGGML_NATIVE=OFF ^
-DGGML_CPU=OFF ^
-DGGML_CUDA=ON ^
-DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" ^
${{ env.CMAKE_ARGS }}
-DLLAMA_CURL=OFF
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
cmake --build build --config Release -j %NINJA_JOBS% --target ggml-cuda
- name: Pack artifacts
id: pack_artifacts
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll
7z a llama-${{ steps.tag.outputs.name }}-bin-win-cuda${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
7z a llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip .\build\bin\Release\ggml-cuda.dll
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: llama-${{ steps.tag.outputs.name }}-bin-win-cuda${{ matrix.cuda }}-x64.zip
name: llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
path: llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip
name: llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip
- name: Copy and pack Cuda runtime
run: |
@ -432,13 +429,13 @@ jobs:
$dst='.\build\bin\cudart\'
robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
7z a cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip $dst\*
7z a cudart-llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip $dst\*
- name: Upload Cuda runtime
uses: actions/upload-artifact@v4
with:
path: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
name: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
path: cudart-llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip
name: cudart-llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip
windows-sycl:
runs-on: windows-latest
@ -455,8 +452,6 @@ jobs:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: ccache
uses: hendrikmuhs/ccache-action@v1.2.16
@ -469,15 +464,18 @@ jobs:
run: |
scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
# TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args
- name: Build
id: cmake_build
run: examples/sycl/win-build-sycl.bat
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
shell: cmd
run: |
call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
cmake -G "Ninja" -B build ^
-DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx ^
-DCMAKE_BUILD_TYPE=Release ^
-DGGML_BACKEND_DL=ON -DBUILD_SHARED_LIBS=ON ^
-DGGML_CPU=OFF -DGGML_SYCL=ON ^
-DLLAMA_CURL=OFF
cmake --build build --target ggml-sycl -j
- name: Build the release package
id: pack_artifacts
@ -502,12 +500,12 @@ jobs:
cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin
echo "cp oneAPI running time dll files to ./build/bin done"
7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/*
7z a llama-bin-win-sycl-x64.zip ./build/bin/*
- name: Upload the release package
uses: actions/upload-artifact@v4
with:
path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip
path: llama-bin-win-sycl-x64.zip
name: llama-bin-win-sycl-x64.zip
windows-hip:
@ -521,8 +519,6 @@ jobs:
- name: Clone
id: checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Clone rocWMMA repository
id: clone_rocwmma
@ -532,7 +528,7 @@ jobs:
- name: ccache
uses: hendrikmuhs/ccache-action@v1.2.16
with:
key: windows-latest-cmake-hip-release
key: windows-latest-cmake-hip-${{ matrix.gpu_target }}-x64
evict-old-files: 1d
- name: Install
@ -550,14 +546,8 @@ jobs:
run: |
& 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version
- name: libCURL
id: get_libcurl
uses: ./.github/actions/windows-setup-curl
- name: Build
id: cmake_build
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
$env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
$env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
@ -569,31 +559,23 @@ jobs:
-DAMDGPU_TARGETS=${{ matrix.gpu_target }} `
-DGGML_HIP_ROCWMMA_FATTN=ON `
-DGGML_HIP=ON `
-DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" `
${{ env.CMAKE_ARGS }}
cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
-DLLAMA_CURL=OFF
cmake --build build --target ggml-hip -j ${env:NUMBER_OF_PROCESSORS}
md "build\bin\rocblas\library\"
cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\"
- name: Determine tag name
id: tag
uses: ./.github/actions/get-tag-name
- name: Pack artifacts
id: pack_artifacts
env:
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
run: |
cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll
7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\*
7z a llama-bin-win-hip-${{ matrix.gpu_target }}-x64.zip .\build\bin\*
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip
name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip
path: llama-bin-win-hip-${{ matrix.gpu_target }}-x64.zip
name: llama-bin-win-hip-${{ matrix.gpu_target }}-x64.zip
ios-xcode-build:
runs-on: macos-latest
@ -655,14 +637,16 @@ jobs:
runs-on: ubuntu-latest
needs:
- ubuntu-22-cpu
- ubuntu-22-vulkan
- windows
- windows-cpu
- windows-cuda
- windows-sycl
- windows-hip
- ubuntu-22-cpu
- ubuntu-22-vulkan
- macOS-arm64
- macOS-x64
- ios-xcode-build
steps:
- name: Clone
@ -680,10 +664,43 @@ jobs:
uses: actions/download-artifact@v4
with:
path: ./artifact
merge-multiple: true
- name: Move artifacts
id: move_artifacts
run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release
run: |
mkdir -p release
echo "Adding CPU backend files to existing zips..."
for arch in x64 arm64; do
cpu_zip="artifact/llama-bin-win-cpu-${arch}.zip"
temp_dir=$(mktemp -d)
echo "Extracting CPU backend for $arch..."
unzip "$cpu_zip" -d "$temp_dir"
echo "Adding CPU files to $arch zips..."
for target_zip in artifact/llama-bin-win-*-${arch}.zip; do
if [[ "$target_zip" == "$cpu_zip" ]]; then
continue
fi
echo "Adding CPU backend to $(basename "$target_zip")"
realpath_target_zip=$(realpath "$target_zip")
(cd "$temp_dir" && zip -r "$realpath_target_zip" .)
done
rm -rf "$temp_dir"
done
echo "Renaming and moving zips to release..."
for zip_file in artifact/llama-bin-win-*.zip; do
base_name=$(basename "$zip_file" .zip)
zip_name="llama-${{ steps.tag.outputs.name }}-${base_name#llama-}.zip"
echo "Moving $zip_file to release/$zip_name"
mv "$zip_file" "release/$zip_name"
done
echo "Moving other artifacts..."
mv -v artifact/*.zip release
- name: Create release
id: create_release
@ -702,7 +719,7 @@ jobs:
const path = require('path');
const fs = require('fs');
const release_id = '${{ steps.create_release.outputs.id }}';
for (let file of await fs.readdirSync('./artifact/release')) {
for (let file of await fs.readdirSync('./release')) {
if (path.extname(file) === '.zip') {
console.log('uploadReleaseAsset', file);
await github.repos.uploadReleaseAsset({
@ -710,7 +727,7 @@ jobs:
repo: context.repo.repo,
release_id: release_id,
name: file,
data: await fs.readFileSync(`./artifact/release/${file}`)
data: await fs.readFileSync(`./release/${file}`)
});
}
}