happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ci : split build.yml + server.yml (#20546) 

* ci : split build.yml

* cont : split server.yml

* cont : reduce paths

* cont : split build-android.yml + update paths

* ci : make msys workflows manual (#20588)

* ci : make cross-build workflows manual (#20585)

* cont : fix release paths

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Georgi Gerganov 2026-03-15 15:11:17 +02:00 committed by GitHub
parent 89d0aec042
commit 9cd4ebcfb1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
17 changed files with 1248 additions and 957 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
.github/workflows/build-3rd-party.yml vendored Normal file
View File

@ -0,0 +1,57 @@
name: CI (3rd-party)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-3rd-party.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-llguidance:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_LLGUIDANCE=ON
cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900

140
.github/workflows/build-android.yml vendored Normal file
View File

@ -0,0 +1,140 @@
name: CI (android)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-android.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-android.yml',
'examples/llama.android/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
android:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
# Disabled due to size (400MB) and always 0 cache hits
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.16
# with:
# key: android-build
# evict-old-files: 1d
- name: Set up JDK
uses: actions/setup-java@v5
with:
java-version: 17
distribution: zulu
- name: Setup Android SDK
uses: android-actions/setup-android@v3
with:
log-accepted-android-sdk-licenses: false
- name: Build
run: |
cd examples/llama.android
./gradlew build --no-daemon
android-ndk:
runs-on: ubuntu-latest
env:
OPENCL_VERSION: 2025.07.22
strategy:
matrix:
include:
- build: 'arm64-cpu'
defines: '-D ANDROID_ABI=arm64-v8a -D ANDROID_PLATFORM=android-31 -D CMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -D GGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm -G Ninja -D LLAMA_OPENSSL=OFF -D GGML_OPENMP=OFF'
- build: 'arm64-snapdragon'
defines: '--preset arm64-android-snapdragon-release'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install OpenCL Headers and Libs
id: install_opencl
if: ${{ matrix.build == 'arm64-snapdragon' }}
run: |
mkdir opencl
curl -L -o opencl/clhpp.tar.gz https://github.com/KhronosGroup/OpenCL-CLHPP/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
curl -L -o opencl/headers.tar.gz https://github.com/KhronosGroup/OpenCL-Headers/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
curl -L -o opencl/icd-loader.tar.gz https://github.com/KhronosGroup/OpenCL-ICD-Loader/archive/refs/tags/v${OPENCL_VERSION}.tar.gz
tar -xaf opencl/headers.tar.gz -C opencl
tar -xaf opencl/clhpp.tar.gz -C opencl
tar -xaf opencl/icd-loader.tar.gz -C opencl
sudo cp -r opencl/OpenCL-Headers-${OPENCL_VERSION}/CL ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include
sudo cp -r opencl/OpenCL-CLHPP-${OPENCL_VERSION}/include/CL/* ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include/CL
cd opencl/OpenCL-ICD-Loader-${OPENCL_VERSION}
cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake -DOPENCL_ICD_LOADER_HEADERS_DIR=${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=31 -DANDROID_STL=c++_shared
cmake --build build
sudo cp build/libOpenCL.so ${ANDROID_NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android
rm -rf opencl
- name: Install Hexagon SDK
id: install_hexsdk
if: ${{ matrix.build == 'arm64-snapdragon' }}
env:
HEXSDK_VER: 6.4.0.2
HEXTLS_VER: 19.0.04
run: |
curl -L -o hex-sdk.tar.gz https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v$HEXSDK_VER/hexagon-sdk-v$HEXSDK_VER-amd64-lnx.tar.xz
mkdir hex-sdk
tar -xaf hex-sdk.tar.gz -C hex-sdk
ls -l hex-sdk
sudo mv hex-sdk /opt/hexagon
echo "HEXAGON_SDK_ROOT=/opt/hexagon/$HEXSDK_VER" >> "$GITHUB_ENV"
echo "HEXAGON_TOOLS_ROOT=/opt/hexagon/$HEXSDK_VER/tools/HEXAGON_Tools/$HEXTLS_VER" >> "$GITHUB_ENV"
echo "DEFAULT_HLOS_ARCH=64" >> "$GITHUB_ENV"
echo "DEFAULT_TOOLS_VARIANT=toolv19" >> "$GITHUB_ENV"
echo "DEFAULT_NO_QURT_INC=0" >> "$GITHUB_ENV"
echo "DEFAULT_DSP_ARCH=v73" >> "$GITHUB_ENV"
- name: Update CMake presets
id: update_presets
if: ${{ matrix.build == 'arm64-snapdragon' }}
run: |
cp docs/backend/snapdragon/CMakeUserPresets.json .
- name: Build
id: ndk_build
run: |
cmake ${{ matrix.defines }} -B build
cmake --build build
cmake --install build --prefix pkg-adb/llama.cpp
- name: Test
id: cmake_test
run: |
echo "FIXME: test on devices"

214
.github/workflows/build-apple.yml vendored Normal file
View File

@ -0,0 +1,214 @@
name: CI (apple)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-apple.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.swift',
'**/*.m',
'**/*.metal'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-apple.yml',
'ggml/src/ggml-metal/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
macOS-latest-ios:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: macOS-latest-ios
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=iOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-ios-xcode:
runs-on: macos-latest
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Xcode
uses: ggml-org/setup-xcode@v1
with:
xcode-version: latest-stable
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=iOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
- name: xcodebuild for swift package
id: xcodebuild
run: |
./build-xcframework.sh
- name: Upload xcframework artifact
uses: actions/upload-artifact@v6
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
retention-days: 1
- name: Build Xcode project
run: |
xcodebuild -downloadPlatform iOS
xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
macOS-latest-tvos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: macOS-latest-tvos
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=tvOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macOS-latest-visionos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=visionOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macOS-latest-swift:
runs-on: macos-latest
needs: macos-latest-ios-xcode
strategy:
matrix:
destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: macOS-latest-swift
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Download xcframework artifact
uses: actions/download-artifact@v7
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
- name: Build llama.cpp with CMake
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_USE_BF16=ON \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)

42
.github/workflows/build-cache.yml vendored
View File

@ -37,31 +37,31 @@ jobs:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
ubuntu-24-spacemit-cache:
runs-on: ubuntu-24.04
#ubuntu-24-spacemit-cache:
# runs-on: ubuntu-24.04
env:
# Make sure this is in sync with build-linux-cross.yml
SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
# env:
# # Make sure this is in sync with build-linux-cross.yml
# SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
- name: Setup Cache
uses: actions/cache@v5
id: cache-toolchain
with:
path: ./spacemit_toolchain
key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
# - name: Setup Cache
# uses: actions/cache@v5
# id: cache-toolchain
# with:
# path: ./spacemit_toolchain
# key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
- name: Setup SpacemiT Toolchain
if: steps.cache-toolchain.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-spacemit
with:
path: ./spacemit_toolchain
version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
# - name: Setup SpacemiT Toolchain
# if: steps.cache-toolchain.outputs.cache-hit != 'true'
# uses: ./.github/actions/linux-setup-spacemit
# with:
# path: ./spacemit_toolchain
# version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
ubuntu-24-openvino-cache:
runs-on: ubuntu-24.04

102
.github/workflows/build-cann.yml vendored Normal file
View File

@ -0,0 +1,102 @@
name: CI (cann)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-cann.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-cann.yml',
'ggml/src/ggml-cann/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
openEuler-latest-cann:
defaults:
run:
shell: bash -el {0}
strategy:
matrix:
arch: [x86, aarch64]
chip_type: ['910b', '310p']
build: ['Release']
use_acl_graph: ['on', 'off']
exclude:
# 310P does not support USE_ACL_GRAPH=on
- chip_type: '310p'
use_acl_graph: 'on'
runs-on: ${{ matrix.arch == 'aarch64' && 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Free up disk space
uses: ggml-org/free-disk-space@v1.3.1
with:
tool-cache: true
- name: Set container image
id: cann-image
run: |
image="ascendai/cann:${{ matrix.chip_type == '910b' && '8.3.rc2-910b-openeuler24.03-py3.11' || '8.3.rc2-310p-openeuler24.03-py3.11' }}"
echo "image=${image}" >> "${GITHUB_OUTPUT}"
- name: Pull container image
run: docker pull "${{ steps.cann-image.outputs.image }}"
- name: Build
env:
BUILD_TYPE: ${{ matrix.build }}
SOC_TYPE: ascend${{ matrix.chip_type }}
USE_ACL_GRAPH: ${{ matrix.use_acl_graph }}
run: |
HOST_UID=$(id -u)
HOST_GID=$(id -g)
docker run --rm \
-v "${PWD}:/workspace" \
-w /workspace \
-e SOC_TYPE=${SOC_TYPE} \
-e BUILD_TYPE=${BUILD_TYPE} \
-e USE_ACL_GRAPH=${USE_ACL_GRAPH} \
"${{ steps.cann-image.outputs.image }}" \
bash -lc '
set -e
yum install -y --setopt=install_weak_deps=False --setopt=tsflags=nodocs git gcc gcc-c++ make cmake openssl-devel
yum clean all && rm -rf /var/cache/yum
git config --global --add safe.directory "/workspace"
export LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/$(uname -m)-linux/devlib/:${LD_LIBRARY_PATH}
cmake -S . -B build \
-DCMAKE_BUILD_TYPE=${BUILD_TYPE} \
-DGGML_CANN=on \
-DSOC_TYPE=${SOC_TYPE} \
-DUSE_ACL_GRAPH=${USE_ACL_GRAPH}
cmake --build build -j $(nproc)
chown -R '"${HOST_UID}"':'"${HOST_GID}"' /workspace/build
'

35
.github/workflows/build-linux-cross.yml → .github/workflows/build-cross.yml vendored
View File

@ -1,7 +1,24 @@
name: Build on Linux using cross-compiler
name: CI (cross)
on:
# only manual triggers due to low-importance of the workflows
# TODO: for regular runs, provision dedicated self-hosted runners
workflow_dispatch:
workflow_call:
push:
branches:
- master
paths: [
'.github/workflows/build-cross.yml',
'ggml/src/spacemit/*',
'ggml/src/arch/loongarch/*'
]
# run once every week
schedule:
- cron: '0 0 * * 0'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
# ubuntu-24-riscv64-cpu-cross:
@ -264,15 +281,15 @@ jobs:
steps:
- uses: actions/checkout@v6
- name: Use SpacemiT Toolchain Cache
uses: actions/cache@v5
id: cache-toolchain
with:
path: ./spacemit_toolchain
key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
#- name: Use SpacemiT Toolchain Cache
# uses: actions/cache@v5
# id: cache-toolchain
# with:
# path: ./spacemit_toolchain
# key: spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}-${{ runner.os }}
- name: Setup SpacemiT Toolchain
if: steps.cache-toolchain.outputs.cache-hit != 'true'
#if: steps.cache-toolchain.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-spacemit
with:
path: ./spacemit_toolchain

72
.github/workflows/build-msys.yml vendored Normal file
View File

@ -0,0 +1,72 @@
name: CI (msys)
on:
# only manual triggers due to low-importance of the workflows
# TODO: for regular runs, provision dedicated self-hosted runners
workflow_dispatch:
# run once every week
schedule:
- cron: '0 0 * * 0'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
windows-msys2:
runs-on: windows-2025
strategy:
fail-fast: false
matrix:
include:
- { sys: UCRT64, env: ucrt-x86_64, build: Release }
- { sys: CLANG64, env: clang-x86_64, build: Release }
steps:
- name: Clone
uses: actions/checkout@v6
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.16
# with:
# key: windows-msys2
# variant: ccache
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Setup ${{ matrix.sys }}
uses: msys2/setup-msys2@v2
with:
update: true
msystem: ${{matrix.sys}}
install: >-
base-devel
git
mingw-w64-${{matrix.env}}-toolchain
mingw-w64-${{matrix.env}}-cmake
mingw-w64-${{matrix.env}}-openblas
- name: Build using CMake
shell: msys2 {0}
run: |
cmake -B build
cmake --build build --config ${{ matrix.build }} -j $(nproc)
- name: Clean after building using CMake
shell: msys2 {0}
run: |
rm -rf build
- name: Build using CMake w/ OpenBLAS
shell: msys2 {0}
run: |
cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
cmake --build build --config ${{ matrix.build }} -j $(nproc)

136
.github/workflows/build-riscv.yml vendored Normal file
View File

@ -0,0 +1,136 @@
name: CI (riscv)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-riscv.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-riscv.yml',
'ggml/src/ggml-cpu/arch/riscv/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
ubuntu-riscv64-native-sanitizer:
runs-on: RISCV64
continue-on-error: true
strategy:
matrix:
sanitizer: [ADDRESS, THREAD, UNDEFINED]
build_type: [Debug]
steps:
- name: Install dependencies
run: |
sudo apt-get update
# Install necessary packages
sudo apt-get install -y libatomic1 libtsan2 gcc-14 g++-14 rustup cmake build-essential wget ccache git-lfs
# Set gcc-14 and g++-14 as the default compilers
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
sudo ln -sf /usr/bin/gcc-14 /usr/bin/gcc
sudo ln -sf /usr/bin/g++-14 /usr/bin/g++
# Install Rust stable version
rustup install stable
rustup default stable
git lfs install
- name: GCC version check
run: |
gcc --version
g++ --version
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup ccache
run: |
# Unique cache directory per matrix combination
export CCACHE_DIR="$HOME/.ccache/sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}"
mkdir -p "$CCACHE_DIR"
# Configure ccache
ccache --set-config=max_size=5G
ccache --set-config=compression=true
ccache --set-config=compression_level=6
ccache --set-config=cache_dir="$CCACHE_DIR"
ccache --set-config=sloppiness=file_macro,time_macros,include_file_mtime,include_file_ctime
ccache --set-config=hash_dir=false
# Export for subsequent steps
echo "CCACHE_DIR=$CCACHE_DIR" >> $GITHUB_ENV
echo "PATH=/usr/lib/ccache:$PATH" >> $GITHUB_ENV
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer != 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=ON \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Build (no OpenMP)
id: cmake_build_no_openmp
if: ${{ matrix.sanitizer == 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900

87
.github/workflows/build-sanitize.yml vendored Normal file
View File

@ -0,0 +1,87 @@
name: CI (sanitize)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-sanitize.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
ubuntu-latest-sanitizer:
runs-on: ubuntu-latest
continue-on-error: true
strategy:
matrix:
sanitizer: [ADDRESS, THREAD, UNDEFINED]
build_type: [Debug]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-latest-sanitizer-${{ matrix.sanitizer }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer != 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Build (no OpenMP)
id: cmake_build_no_openmp
if: ${{ matrix.sanitizer == 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=OFF
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900

96
.github/workflows/build-vulkan.yml vendored Normal file
View File

@ -0,0 +1,96 @@
name: CI (vulkan)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-vulkan.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.comp',
'**/*.glsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-vulkan.yml',
'ggml/src/ggml-vulkan/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-vulkan-llvmpipe:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-24-vulkan-llvmpipe
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dependencies
id: depends
run: |
sudo add-apt-repository -y ppa:kisak/kisak-mesa
sudo apt-get update -y
sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
- name: Get latest Vulkan SDK version
id: vulkan_sdk_version
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Use Vulkan SDK Cache
uses: actions/cache@v5
id: cache-sdk
with:
path: ./vulkan_sdk
key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
- name: Setup Vulkan SDK
if: steps.cache-sdk.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-vulkan-llvmpipe
with:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
- name: Build
id: cmake_build
run: |
source ./vulkan_sdk/setup-env.sh
cmake -B build \
-DGGML_VULKAN=ON
cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
export GGML_VK_VISIBLE_DEVICES=0
export GGML_VK_DISABLE_F16=1
export GGML_VK_DISABLE_COOPMAT=1
# This is using llvmpipe and runs slower than other backends
ctest -L main --verbose --timeout 4800

997
.github/workflows/build.yml vendored
View File

File diff suppressed because it is too large Load Diff

10
.github/workflows/python-lint.yml vendored
View File

@ -4,10 +4,16 @@ on:
push:
branches:
- master
paths: ['.github/workflows/python-lint.yml', '**/*.py']
paths: [
'.github/workflows/python-lint.yml',
'**/*.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: ['.github/workflows/python-lint.yml', '**/*.py']
paths: [
'.github/workflows/python-lint.yml',
'**/*.py'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}

37
.github/workflows/release.yml vendored
View File

@ -10,7 +10,22 @@ on:
push:
branches:
- master
paths: ['.github/workflows/release.yml', '**/CMakeLists.txt', '**/.cmake', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp']
paths: [
'.github/workflows/release.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
@ -34,7 +49,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: macOS-latest-cmake-arm64
key: macOS-latest-arm64
evict-old-files: 1d
- name: Build
@ -81,7 +96,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: macOS-latest-cmake-x64
key: macOS-latest-x64
evict-old-files: 1d
- name: Build
@ -140,7 +155,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-cpu-cmake-${{ matrix.build }}
key: ubuntu-cpu-${{ matrix.build }}
evict-old-files: 1d
- name: Dependencies
@ -191,7 +206,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-22-cmake-vulkan
key: ubuntu-22-vulkan
evict-old-files: 1d
- name: Dependencies
@ -256,7 +271,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-24-cmake-openvino-release-no-preset-v1
key: ubuntu-24-openvino-release-no-preset-v1
evict-old-files: 1d
- name: Dependencies
@ -329,7 +344,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: windows-latest-cmake-cpu-${{ matrix.arch }}
key: windows-latest-cpu-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
@ -390,7 +405,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: windows-latest-cmake-${{ matrix.backend }}-${{ matrix.arch }}
key: windows-latest-${{ matrix.backend }}-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
@ -536,7 +551,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: windows-latest-cmake-sycl
key: windows-latest-sycl
variant: ccache
evict-old-files: 1d
@ -616,7 +631,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ubuntu-rocm-cmake-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}
key: ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}
evict-old-files: 1d
- name: Dependencies
@ -726,7 +741,7 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: windows-latest-cmake-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}-x64
key: windows-latest-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}-x64
evict-old-files: 1d
- name: Install ROCm

105
.github/workflows/server-sanitize.yml vendored Normal file
View File

@ -0,0 +1,105 @@
name: Server (sanitize)
on:
workflow_dispatch: # allows manual triggering
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
slow_tests:
description: 'Run slow tests'
required: true
type: boolean
push:
branches:
- master
paths: [
'.github/workflows/server-sanitize.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'tools/server/**.*'
]
env:
LLAMA_LOG_COLORS: 1
LLAMA_LOG_PREFIX: 1
LLAMA_LOG_TIMESTAMPS: 1
LLAMA_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
server:
runs-on: ubuntu-latest
strategy:
matrix:
sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
build_type: [RelWithDebInfo]
fail-fast: false
steps:
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get -y install \
build-essential \
xxd \
git \
cmake \
curl \
wget \
language-pack-en \
libssl-dev
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
-DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
run: |
cd tools/server/tests
export ${{ matrix.extra_args }}
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
run: |
cd tools/server/tests
export ${{ matrix.extra_args }}
SLOW_TESTS=1 pytest -v -x

14
.github/workflows/server-self-hosted.yml vendored
View File

@ -14,7 +14,19 @@ on:
push:
branches:
- master
paths: ['.github/workflows/server-self-hosted.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
paths: [
'.github/workflows/server-self-hosted.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
env:
LLAMA_LOG_COLORS: 1

15
.github/workflows/server-webui.yml vendored
View File

@ -1,4 +1,3 @@
# Server WebUI build and tests
name: Server WebUI
on:
@ -11,10 +10,20 @@ on:
push:
branches:
- master
paths: ['.github/workflows/server-webui.yml', 'tools/server/webui/**.*', 'tools/server/tests/**.*', 'tools/server/public/**']
paths: [
'.github/workflows/server-webui.yml',
'tools/server/webui/**.*',
'tools/server/tests/**.*',
'tools/server/public/**'
]
pull_request:
types: [opened, synchronize, reopened]
paths: ['.github/workflows/server-webui.yml', 'tools/server/webui/**.*', 'tools/server/tests/**.*', 'tools/server/public/**']
paths: [
'.github/workflows/server-webui.yml',
'tools/server/webui/**.*',
'tools/server/tests/**.*',
'tools/server/public/**'
]
env:
LLAMA_LOG_COLORS: 1

46
.github/workflows/server.yml vendored
View File

@ -1,4 +1,3 @@
# Server build and tests
name: Server
on:
@ -15,10 +14,34 @@ on:
push:
branches:
- master
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
pull_request:
types: [opened, synchronize, reopened]
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
env:
LLAMA_LOG_COLORS: 1
@ -34,17 +57,18 @@ jobs:
server:
runs-on: ubuntu-latest
name: server (${{ matrix.wf_name }})
strategy:
matrix:
sanitizer: [ADDRESS, UNDEFINED] # THREAD is very slow
build_type: [RelWithDebInfo]
build_type: [Release]
wf_name: ["default"]
include:
- build_type: Release
sanitizer: ""
extra_args: ""
wf_name: "default"
- build_type: Release
sanitizer: ""
extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
wf_name: "backend-sampling"
fail-fast: false
steps:
@ -74,13 +98,7 @@ jobs:
run: |
cmake -B build \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DGGML_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DGGML_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }} \
-DLLAMA_SANITIZE_ADDRESS=${{ matrix.sanitizer == 'ADDRESS' }} \
-DLLAMA_SANITIZE_THREAD=${{ matrix.sanitizer == 'THREAD' }} \
-DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
-DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
- name: Python setup