koboldcpp/.github/workflows/build.yml

518 lines
17 KiB
YAML

name: CI
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build.yml',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build.yml',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
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_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
build-cmake-pkg:
uses: ./.github/workflows/build-cmake-pkg.yml
ubuntu-cpu:
strategy:
matrix:
include:
- build: 'x64'
os: ubuntu-22.04
- build: 'arm64'
os: ubuntu-24.04-arm
runs-on: ${{ matrix.os }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-cpu-${{ matrix.build }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build Dependencies
id: build_depends
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
python3 python3-pip python3-dev python3-wheel \
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
if: ${{ contains(matrix.os, 'ubuntu-24.04') }}
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
export PIP_BREAK_SYSTEM_PACKAGES="1"
python3 -m pip install --upgrade pip setuptools
pip3 install ./gguf-py
- name: Build
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
- name: Test llama2c conversion
id: llama2c_test
run: |
cd build
echo "Fetch tokenizer"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
echo "Fetch llama2c model"
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
ubuntu-24-vulkan:
strategy:
matrix:
include:
- build: 'x64'
os: ubuntu-24.04
- build: 'arm64'
os: ubuntu-24.04-arm
runs-on: ${{ matrix.os }}
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y gcc-14 g++-14 build-essential glslc libvulkan-dev spirv-headers libssl-dev ninja-build
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Configure
id: cmake_configure
run: |
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=RelWithDebInfo \
-DGGML_BACKEND_DL=ON \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_VULKAN=ON
- name: Build
id: cmake_build
run: |
time cmake --build build -j $(nproc)
windows-latest:
runs-on: windows-2025
env:
OPENBLAS_VERSION: 0.3.23
SDE_VERSION: 9.33.0-2024-01-07
VULKAN_VERSION: 1.4.313.2
strategy:
matrix:
include:
- build: 'x64-cpu-static'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
- build: 'x64-openblas'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
- build: 'x64-vulkan'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
- build: 'arm64'
arch: 'arm64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON'
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-latest-${{ matrix.build }}
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Download OpenBLAS
id: get_openblas
if: ${{ matrix.build == 'x64-openblas' }}
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 == 'x64-vulkan' }}
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
run: |
cmake -S . -B build ${{ matrix.defines }} `
-DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Add libopenblas.dll
id: add_libopenblas_dll
if: ${{ matrix.build == 'x64-openblas' }}
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: Test
id: cmake_test
if: ${{ matrix.arch == 'x64' }}
run: |
cd build
ctest -L main -C Release --verbose --timeout 900
# TODO: disabled for now, consider adding tests for all CPU variants instead
# - name: Test (Intel SDE)
# id: cmake_test_sde
# if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation
# run: |
# curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz"
# # for some weird reason windows tar doesn't like sde tar.xz
# 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz
# 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
# $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
# cd build
# $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
# & $sde -future -- ctest -L main -C Release --verbose --timeout 900
ubuntu-latest-cuda:
runs-on: ubuntu-latest
container: nvidia/cuda:12.6.2-devel-ubuntu24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
env:
DEBIAN_FRONTEND: noninteractive
run: |
apt update
apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-latest-cuda
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with CMake
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
cmake -S . -B build -G Ninja \
-DLLAMA_FATAL_WARNINGS=ON \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_CUDA_ARCHITECTURES=89-real \
-DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
-DGGML_NATIVE=OFF \
-DGGML_CUDA=ON \
-DGGML_CUDA_CUB_3DOT2=ON
cmake --build build
windows-2022-cuda:
runs-on: windows-2022
strategy:
matrix:
cuda: ['12.4']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-cuda-${{ matrix.cuda }}
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
with:
cuda_version: ${{ matrix.cuda }}
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
shell: cmd
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
cmake -S . -B build -G "Ninja Multi-Config" ^
-DLLAMA_BUILD_SERVER=ON ^
-DLLAMA_BUILD_BORINGSSL=ON ^
-DGGML_NATIVE=OFF ^
-DGGML_BACKEND_DL=ON ^
-DGGML_CPU_ALL_VARIANTS=ON ^
-DGGML_CUDA=ON ^
-DGGML_RPC=ON ^
-DGGML_CUDA_CUB_3DOT2=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release
# TODO: simplify the following workflows using a matrix
# TODO: run lighter CI on PRs and the full CI only on master (if needed)
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
# ggml-ci-x64-cpu-low-perf:
# runs-on: ubuntu-22.04
#
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
#
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: ggml-ci-x64-cpu-low-perf
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
#
# - name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get install build-essential
#
# - name: Test
# id: ggml-ci
# run: |
# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
# ggml-ci-arm64-cpu-low-perf:
# runs-on: ubuntu-22.04-arm
#
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
#
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: ggml-ci-arm64-cpu-low-perf
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
#
# - name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get install build-essential
#
# - name: Test
# id: ggml-ci
# run: |
# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
# ggml-ci-x64-cpu-high-perf:
# runs-on: ubuntu-22.04
#
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
#
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: ggml-ci-x64-cpu-high-perf
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
#
# - name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get install build-essential
#
# - name: Test
# id: ggml-ci
# run: |
# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
# note: moved to build-self-hosted.yml - can remove from here when everything is stable
# ggml-ci-arm64-cpu-high-perf:
# runs-on: ubuntu-22.04-arm
#
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
#
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: ggml-ci-arm64-cpu-high-perf
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
#
# - name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get install build-essential
#
# - name: Test
# id: ggml-ci
# run: |
# LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-high-perf-sve:
runs-on: ubuntu-22.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ggml-ci-arm64-cpu-high-perf-sve
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-kleidiai:
runs-on: ubuntu-22.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ggml-ci-arm64-cpu-kleidiai
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 -y build-essential
- name: Test
id: ggml-ci
run: |
GG_BUILD_KLEIDIAI=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt