mirror of
https://github.com/ollama/ollama.git
synced 2025-05-10 18:06:33 +02:00
* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
167 lines
6.4 KiB
YAML
167 lines
6.4 KiB
YAML
name: test
|
|
|
|
concurrency:
|
|
# For PRs, later CI runs preempt previous ones. e.g. a force push on a PR
|
|
# cancels running CI jobs and starts all new ones.
|
|
#
|
|
# For non-PR pushes, concurrency.group needs to be unique for every distinct
|
|
# CI run we want to have happen. Use run_id, which in practice means all
|
|
# non-PR CI runs will be allowed to run without preempting each other.
|
|
group: ${{ github.workflow }}-$${{ github.pull_request.number || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- '**/*'
|
|
- '!docs/**'
|
|
- '!README.md'
|
|
|
|
jobs:
|
|
changes:
|
|
runs-on: ubuntu-latest
|
|
outputs:
|
|
changed: ${{ steps.changes.outputs.changed }}
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
with:
|
|
fetch-depth: 0
|
|
- id: changes
|
|
run: |
|
|
changed() {
|
|
local BASE=${{ github.event.pull_request.base.sha }}
|
|
local HEAD=${{ github.event.pull_request.head.sha }}
|
|
local MERGE_BASE=$(git merge-base $BASE $HEAD)
|
|
git diff-tree -r --no-commit-id --name-only "$MERGE_BASE" "$HEAD" \
|
|
| xargs python3 -c "import sys; from pathlib import Path; print(any(Path(x).match(glob) for x in sys.argv[1:] for glob in '$*'.split(' ')))"
|
|
}
|
|
|
|
echo changed=$(changed 'llama/llama.cpp/**' 'ml/backend/ggml/ggml/**') | tee -a $GITHUB_OUTPUT
|
|
|
|
linux:
|
|
needs: [changes]
|
|
if: needs.changes.outputs.changed == 'True'
|
|
strategy:
|
|
matrix:
|
|
include:
|
|
- preset: CPU
|
|
- preset: CUDA
|
|
container: nvidia/cuda:11.8.0-devel-ubuntu22.04
|
|
flags: '-DCMAKE_CUDA_ARCHITECTURES=87'
|
|
- preset: ROCm
|
|
container: rocm/dev-ubuntu-22.04:6.1.2
|
|
extra-packages: rocm-libs
|
|
flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_PREFIX_PATH=/opt/rocm'
|
|
runs-on: linux
|
|
container: ${{ matrix.container }}
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- run: |
|
|
[ -n "${{ matrix.container }}" ] || sudo=sudo
|
|
$sudo apt-get update
|
|
$sudo apt-get install -y cmake ccache ${{ matrix.extra-packages }}
|
|
env:
|
|
DEBIAN_FRONTEND: noninteractive
|
|
- uses: actions/cache@v4
|
|
with:
|
|
path: /github/home/.cache/ccache
|
|
key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}
|
|
- run: |
|
|
cmake --preset ${{ matrix.preset }} ${{ matrix.flags }}
|
|
cmake --build --preset ${{ matrix.preset }} --parallel
|
|
|
|
windows:
|
|
needs: [changes]
|
|
if: needs.changes.outputs.changed == 'True'
|
|
strategy:
|
|
matrix:
|
|
include:
|
|
- preset: CPU
|
|
- preset: CUDA
|
|
install: https://developer.download.nvidia.com/compute/cuda/11.8.0/local_installers/cuda_11.8.0_522.06_windows.exe
|
|
flags: '-DCMAKE_CUDA_ARCHITECTURES=87'
|
|
- preset: ROCm
|
|
install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe
|
|
flags: '-DAMDGPU_TARGETS=gfx1010'
|
|
runs-on: windows
|
|
steps:
|
|
- run: |
|
|
choco install -y --no-progress ccache ninja
|
|
ccache -o cache_dir=${{ github.workspace }}\.ccache
|
|
- if: matrix.preset == 'CUDA' || matrix.preset == 'ROCm'
|
|
id: cache-install
|
|
uses: actions/cache/restore@v4
|
|
with:
|
|
path: |
|
|
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
|
|
C:\Program Files\AMD\ROCm
|
|
key: ${{ matrix.install }}
|
|
- if: matrix.preset == 'CUDA'
|
|
name: Install CUDA ${{ matrix.cuda-version }}
|
|
run: |
|
|
$ErrorActionPreference = "Stop"
|
|
if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
|
|
Invoke-WebRequest -Uri "${{ matrix.install }}" -OutFile "install.exe"
|
|
Start-Process -FilePath .\install.exe -ArgumentList (@("-s", "cudart_11.8", "nvcc_11.8", "cublas_11.8", "cublas_dev_11.8")) -NoNewWindow -Wait
|
|
}
|
|
|
|
$cudaPath = (Resolve-Path "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\*").path
|
|
echo "$cudaPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
|
- if: matrix.preset == 'ROCm'
|
|
name: Install ROCm ${{ matrix.rocm-version }}
|
|
run: |
|
|
$ErrorActionPreference = "Stop"
|
|
if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
|
|
Invoke-WebRequest -Uri "${{ matrix.install }}" -OutFile "install.exe"
|
|
Start-Process -FilePath .\install.exe -ArgumentList '-install' -NoNewWindow -Wait
|
|
}
|
|
|
|
$hipPath = (Resolve-Path "C:\Program Files\AMD\ROCm\*").path
|
|
echo "$hipPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
|
echo "CC=$hipPath\bin\clang.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
|
echo "CXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
|
- if: ${{ !cancelled() && steps.cache-install.outputs.cache-hit != 'true' }}
|
|
uses: actions/cache/save@v4
|
|
with:
|
|
path: |
|
|
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
|
|
C:\Program Files\AMD\ROCm
|
|
key: ${{ matrix.install }}
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/cache@v4
|
|
with:
|
|
path: ${{ github.workspace }}\.ccache
|
|
key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}
|
|
- run: |
|
|
Import-Module 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
|
|
Enter-VsDevShell -VsInstallPath 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise' -SkipAutomaticLocation -DevCmdArguments '-arch=x64 -no_logo'
|
|
cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
|
|
cmake --build --parallel --preset "${{ matrix.preset }}"
|
|
env:
|
|
CMAKE_GENERATOR: Ninja
|
|
|
|
test:
|
|
strategy:
|
|
matrix:
|
|
os: [ubuntu-latest, macos-latest, windows-latest]
|
|
runs-on: ${{ matrix.os }}
|
|
env:
|
|
CGO_ENABLED: '1'
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/setup-go@v5
|
|
with:
|
|
go-version-file: go.mod
|
|
- uses: golangci/golangci-lint-action@v6
|
|
with:
|
|
args: --timeout 10m0s -v
|
|
- run: go test ./...
|
|
|
|
patches:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- name: Verify patches apply cleanly and do not change files
|
|
run: |
|
|
make -f Makefile.sync clean checkout sync
|
|
git diff --compact-summary --exit-code
|