mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-27 07:31:24 +02:00
Georgi Gerganov
985b14912b
* ci : apply ccache-clear with older/min/dry-run to all ccache jobs Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : install gh in ccache-clear if missing (container jobs) The ccache-clear action relies on the gh CLI, which is not present in container-based jobs. Install it on demand so those jobs can clear caches. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : install gh via apt repo in ccache-clear The install.sh script used previously is no longer served (404). Switch to the official GitHub CLI apt repository, which is still available. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : pass --repo to gh cache commands in ccache-clear In container jobs gh cannot auto-detect the repository from git, so gh cache list/delete fail with 'failed to run git: not a git repository'. Pass the repository explicitly via --repo using GITHUB_REPOSITORY. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : drop -new suffix from vulkan ccache key The -new suffix was only needed to force a fresh cache. With ccache-clear now evicting stale caches, the original key can be used again. The old ccache-vulkan-ubuntu-24.04-arm-new entries still match the ccache-clear key prefix and are cleaned up automatically. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : fix ccache-clear date parsing on macOS (BSD date) macOS ships BSD date, which has no -d option. The older cutoff check was silently disabled there: 'date: illegal option -- d' errors in the log and the loop was only stopped by the min limit, risking deletion of caches not older than the cutoff (e.g. saved by a concurrent job). Parse the ISO-8601 timestamps with GNU date when available and fall back to BSD date otherwise (TZ=UTC, fractional seconds dropped). Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : extract ccache-clear logic into scripts/ccache-clear.sh The composite action now consists of a dedicated step that installs the GitHub CLI when missing (e.g. in container jobs) and a thin step that calls the new script. The script follows the make-release-checks.sh conventions (usage/env header, set -euo pipefail, CLI flags) and only checks that gh is available. The action inputs are unchanged, so the workflow steps are untouched. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : remove unused apple ccaches
228 lines
8.1 KiB
YAML
228 lines
8.1 KiB
YAML
name: CI (cpu)
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/build-cpu.yml',
|
|
'.github/workflows/build-cmake-pkg.yml',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'**/*.h',
|
|
'**/*.hpp',
|
|
'**/*.c',
|
|
'**/*.cpp',
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/build-cpu.yml',
|
|
'.github/workflows/build-cmake-pkg.yml',
|
|
'ggml/src/ggml-rpc/**',
|
|
'**/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_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:
|
|
strategy:
|
|
matrix:
|
|
include:
|
|
- build: 'x64'
|
|
os: ubuntu-22.04
|
|
- build: 'arm64'
|
|
os: ubuntu-24.04-arm
|
|
|
|
runs-on: ${{ matrix.os }}
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: cpu-${{ matrix.os }}
|
|
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 \
|
|
-DGGML_NATIVE=OFF \
|
|
-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
|
|
|
|
# note: real deletion only on push to master (same condition as the ccache save),
|
|
# dry-run otherwise (the token is read-only on PRs from forks)
|
|
- name: ccache-clear
|
|
uses: ./.github/actions/ccache-clear
|
|
env:
|
|
GH_TOKEN: ${{ github.token }}
|
|
with:
|
|
key: cpu-${{ matrix.os }}
|
|
older: 5m
|
|
min: 1
|
|
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
|
|
|
|
windows:
|
|
name: windows / ${{ matrix.build }}
|
|
runs-on: windows-2025
|
|
|
|
env:
|
|
OPENBLAS_VERSION: 0.3.23
|
|
SDE_VERSION: 9.33.0-2024-01-07
|
|
|
|
strategy:
|
|
matrix:
|
|
include:
|
|
- build: 'x64-cpu-static'
|
|
arch: 'x64'
|
|
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_OPENMP_FETCH=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
|
|
- build: 'x64-openblas'
|
|
arch: 'x64'
|
|
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
|
|
- build: 'arm64'
|
|
arch: 'arm64'
|
|
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_OPENMP_FETCH=ON -DLLAMA_BUILD_SERVER=ON'
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: cpu-windows-2025-${{ 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 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
|
|
|
|
- name: ccache-clear
|
|
uses: ./.github/actions/ccache-clear
|
|
env:
|
|
GH_TOKEN: ${{ github.token }}
|
|
with:
|
|
key: cpu-windows-2025-${{ matrix.build }}
|
|
older: 5m
|
|
min: 1
|
|
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
|