ollama source for Momentry Core verification
This commit is contained in:
68
.github/ISSUE_TEMPLATE/10_bug_report.yml
vendored
Normal file
68
.github/ISSUE_TEMPLATE/10_bug_report.yml
vendored
Normal file
@@ -0,0 +1,68 @@
|
||||
name: Bug report
|
||||
labels: [bug]
|
||||
description: Something isn't working right.
|
||||
body:
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: What is the issue?
|
||||
description: What happened? What did you expect to happen?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: logs
|
||||
attributes:
|
||||
label: Relevant log output
|
||||
description: Please copy and paste any relevant log output. See [Troubleshooting Guide](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.mdx#how-to-troubleshoot-issues) for details.
|
||||
render: shell
|
||||
validations:
|
||||
required: false
|
||||
- type: dropdown
|
||||
id: os
|
||||
attributes:
|
||||
label: OS
|
||||
description: Which operating system are you using?
|
||||
multiple: true
|
||||
options:
|
||||
- Linux
|
||||
- macOS
|
||||
- Windows
|
||||
- Docker
|
||||
- WSL2
|
||||
validations:
|
||||
required: false
|
||||
- type: dropdown
|
||||
id: gpu
|
||||
attributes:
|
||||
label: GPU
|
||||
description: Which GPU are you using?
|
||||
multiple: true
|
||||
options:
|
||||
- Nvidia
|
||||
- AMD
|
||||
- Intel
|
||||
- Apple
|
||||
- Other
|
||||
validations:
|
||||
required: false
|
||||
- type: dropdown
|
||||
id: cpu
|
||||
attributes:
|
||||
label: CPU
|
||||
description: Which CPU are you using?
|
||||
multiple: true
|
||||
options:
|
||||
- Intel
|
||||
- AMD
|
||||
- Apple
|
||||
- Other
|
||||
validations:
|
||||
required: false
|
||||
- type: input
|
||||
id: version
|
||||
attributes:
|
||||
label: Ollama version
|
||||
description: What version of Ollama are you using? (`ollama --version`)
|
||||
placeholder: e.g., 0.1.32
|
||||
validations:
|
||||
required: false
|
||||
6
.github/ISSUE_TEMPLATE/20_feature_request.md
vendored
Normal file
6
.github/ISSUE_TEMPLATE/20_feature_request.md
vendored
Normal file
@@ -0,0 +1,6 @@
|
||||
---
|
||||
name: Feature request
|
||||
about: Request a new feature
|
||||
labels: feature request
|
||||
---
|
||||
|
||||
5
.github/ISSUE_TEMPLATE/30_model_request.md
vendored
Normal file
5
.github/ISSUE_TEMPLATE/30_model_request.md
vendored
Normal file
@@ -0,0 +1,5 @@
|
||||
---
|
||||
name: Model request
|
||||
about: Request support for a new model to be added to Ollama
|
||||
labels: model request
|
||||
---
|
||||
8
.github/ISSUE_TEMPLATE/config.yml
vendored
Normal file
8
.github/ISSUE_TEMPLATE/config.yml
vendored
Normal file
@@ -0,0 +1,8 @@
|
||||
blank_issues_enabled: true
|
||||
contact_links:
|
||||
- name: Help
|
||||
url: https://discord.com/invite/ollama
|
||||
about: Please join our Discord server for help using Ollama
|
||||
- name: Troubleshooting
|
||||
url: https://github.com/ollama/ollama/blob/main/docs/faq.md#faq
|
||||
about: See the FAQ for common issues and solutions
|
||||
24
.github/workflows/latest.yaml
vendored
Normal file
24
.github/workflows/latest.yaml
vendored
Normal file
@@ -0,0 +1,24 @@
|
||||
name: latest
|
||||
|
||||
on:
|
||||
release:
|
||||
types: [released]
|
||||
|
||||
jobs:
|
||||
update-latest:
|
||||
environment: release
|
||||
runs-on: linux
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ vars.DOCKER_USER }}
|
||||
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
|
||||
- name: Tag images as latest
|
||||
env:
|
||||
PUSH: "1"
|
||||
shell: bash
|
||||
run: |
|
||||
export "VERSION=${GITHUB_REF_NAME#v}"
|
||||
./scripts/tag_latest.sh
|
||||
708
.github/workflows/release.yaml
vendored
Normal file
708
.github/workflows/release.yaml
vendored
Normal file
@@ -0,0 +1,708 @@
|
||||
name: release
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'v*'
|
||||
|
||||
env:
|
||||
CGO_CFLAGS: '-O3'
|
||||
CGO_CXXFLAGS: '-O3'
|
||||
|
||||
jobs:
|
||||
setup-environment:
|
||||
runs-on: ubuntu-latest
|
||||
environment: release
|
||||
outputs:
|
||||
GOFLAGS: ${{ steps.goflags.outputs.GOFLAGS }}
|
||||
VERSION: ${{ steps.goflags.outputs.VERSION }}
|
||||
vendorsha: ${{ steps.changes.outputs.vendorsha }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set environment
|
||||
id: goflags
|
||||
run: |
|
||||
echo GOFLAGS="'-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=${GITHUB_REF_NAME#v}\" \"-X=github.com/ollama/ollama/server.mode=release\"'" | tee -a $GITHUB_OUTPUT
|
||||
echo VERSION="${GITHUB_REF_NAME#v}" | tee -a $GITHUB_OUTPUT
|
||||
echo vendorsha=$(make -f Makefile.sync print-base) | tee -a $GITHUB_OUTPUT
|
||||
|
||||
darwin-build:
|
||||
runs-on: macos-26-xlarge
|
||||
environment: release
|
||||
needs: setup-environment
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
APPLE_IDENTITY: ${{ secrets.APPLE_IDENTITY }}
|
||||
APPLE_PASSWORD: ${{ secrets.APPLE_PASSWORD }}
|
||||
APPLE_TEAM_ID: ${{ vars.APPLE_TEAM_ID }}
|
||||
APPLE_ID: ${{ vars.APPLE_ID }}
|
||||
MACOS_SIGNING_KEY: ${{ secrets.MACOS_SIGNING_KEY }}
|
||||
MACOS_SIGNING_KEY_PASSWORD: ${{ secrets.MACOS_SIGNING_KEY_PASSWORD }}
|
||||
CGO_CFLAGS: '-mmacosx-version-min=14.0 -O3'
|
||||
CGO_CXXFLAGS: '-mmacosx-version-min=14.0 -O3'
|
||||
CGO_LDFLAGS: '-mmacosx-version-min=14.0 -O3'
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: |
|
||||
echo $MACOS_SIGNING_KEY | base64 --decode > certificate.p12
|
||||
security create-keychain -p password build.keychain
|
||||
security default-keychain -s build.keychain
|
||||
security unlock-keychain -p password build.keychain
|
||||
security import certificate.p12 -k build.keychain -P $MACOS_SIGNING_KEY_PASSWORD -T /usr/bin/codesign
|
||||
security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k password build.keychain
|
||||
security set-keychain-settings -lut 3600 build.keychain
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
Makefile.sync
|
||||
- run: |
|
||||
./scripts/build_darwin.sh
|
||||
- name: Log build results
|
||||
run: |
|
||||
ls -l dist/
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: bundles-darwin
|
||||
path: |
|
||||
dist/*.tgz
|
||||
dist/*.tar.zst
|
||||
dist/*.zip
|
||||
dist/*.dmg
|
||||
|
||||
windows-depends:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows]
|
||||
arch: [amd64]
|
||||
preset: ['CPU']
|
||||
include:
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'CUDA 12'
|
||||
install: https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe
|
||||
cuda-components:
|
||||
- '"cudart"'
|
||||
- '"nvcc"'
|
||||
- '"cublas"'
|
||||
- '"cublas_dev"'
|
||||
cuda-version: '12.8'
|
||||
flags: ''
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'CUDA 13'
|
||||
install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
|
||||
cuda-components:
|
||||
- '"cudart"'
|
||||
- '"nvcc"'
|
||||
- '"cublas"'
|
||||
- '"cublas_dev"'
|
||||
- '"crt"'
|
||||
- '"nvvm"'
|
||||
- '"nvptxcompiler"'
|
||||
cuda-version: '13.0'
|
||||
flags: ''
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'ROCm 6'
|
||||
install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
|
||||
rocm-version: '6.2'
|
||||
flags: '-DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
|
||||
runner_dir: 'rocm'
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: Vulkan
|
||||
install: https://sdk.lunarg.com/sdk/download/1.4.321.1/windows/vulkansdk-windows-X64-1.4.321.1.exe
|
||||
flags: ''
|
||||
runner_dir: 'vulkan'
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'MLX CUDA 13'
|
||||
install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
|
||||
cudnn-install: https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.18.1.3_cuda13-archive.zip
|
||||
cuda-components:
|
||||
- '"cudart"'
|
||||
- '"nvcc"'
|
||||
- '"cublas"'
|
||||
- '"cublas_dev"'
|
||||
- '"cufft"'
|
||||
- '"cufft_dev"'
|
||||
- '"nvrtc"'
|
||||
- '"nvrtc_dev"'
|
||||
- '"crt"'
|
||||
- '"nvvm"'
|
||||
- '"nvptxcompiler"'
|
||||
cuda-version: '13.0'
|
||||
flags: ''
|
||||
runs-on: ${{ matrix.arch == 'arm64' && format('{0}-{1}', matrix.os, matrix.arch) || matrix.os }}
|
||||
environment: release
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
steps:
|
||||
# Increase pagefile to handle momentary spikes in RAM from NVCC compiles
|
||||
- if: startsWith(matrix.preset, 'MLX ')
|
||||
name: Increase pagefile to 200 GB
|
||||
uses: al-cheb/configure-pagefile-action@v1.5
|
||||
with:
|
||||
minimum-size: 16GB
|
||||
maximum-size: 200GB
|
||||
disk-root: "D:"
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
choco install -y --no-progress ccache ninja
|
||||
if (Get-Command ccache -ErrorAction SilentlyContinue) {
|
||||
ccache -o cache_dir=${{ github.workspace }}\.ccache
|
||||
}
|
||||
- if: startsWith(matrix.preset, 'CUDA ') || startsWith(matrix.preset, 'ROCm ') || startsWith(matrix.preset, 'Vulkan') || startsWith(matrix.preset, 'MLX ')
|
||||
id: cache-install
|
||||
uses: actions/cache/restore@v4
|
||||
with:
|
||||
path: |
|
||||
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
|
||||
C:\Program Files\AMD\ROCm
|
||||
C:\VulkanSDK
|
||||
C:\Program Files\NVIDIA\CUDNN
|
||||
key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
|
||||
- if: startsWith(matrix.preset, 'CUDA ') || startsWith(matrix.preset, 'MLX ')
|
||||
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"
|
||||
$subpackages = @(${{ join(matrix.cuda-components, ', ') }}) | Foreach-Object {"${_}_${{ matrix.cuda-version }}"}
|
||||
Start-Process -FilePath .\install.exe -ArgumentList (@("-s") + $subpackages) -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: startsWith(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 $env:GITHUB_ENV -Append
|
||||
echo "HIPCXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "HIP_PLATFORM=amd" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CMAKE_PREFIX_PATH=$hipPath" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
- if: matrix.preset == 'Vulkan'
|
||||
name: Install Vulkan ${{ 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 "-c","--am","--al","in" -NoNewWindow -Wait
|
||||
}
|
||||
|
||||
$vulkanPath = (Resolve-Path "C:\VulkanSDK\*").path
|
||||
echo "$vulkanPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
echo "VULKAN_SDK=$vulkanPath" >> $env:GITHUB_ENV
|
||||
- if: matrix.preset == 'CPU'
|
||||
run: |
|
||||
echo "CC=clang.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CXX=clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
- if: startsWith(matrix.preset, 'MLX ')
|
||||
name: Install cuDNN for MLX
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
$cudnnRoot = "C:\Program Files\NVIDIA\CUDNN"
|
||||
if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
|
||||
Invoke-WebRequest -Uri "${{ matrix.cudnn-install }}" -OutFile "cudnn.zip"
|
||||
Expand-Archive -Path cudnn.zip -DestinationPath cudnn-extracted
|
||||
$cudnnDir = (Get-ChildItem -Path cudnn-extracted -Directory)[0].FullName
|
||||
New-Item -ItemType Directory -Force -Path $cudnnRoot
|
||||
Copy-Item -Path "$cudnnDir\*" -Destination "$cudnnRoot\" -Recurse
|
||||
}
|
||||
|
||||
echo "CUDNN_ROOT_DIR=$cudnnRoot" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CUDNN_INCLUDE_PATH=$cudnnRoot\include" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CUDNN_LIBRARY_PATH=$cudnnRoot\lib\x64" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "$cudnnRoot\bin\x64" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -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
|
||||
C:\VulkanSDK
|
||||
C:\Program Files\NVIDIA\CUDNN
|
||||
key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ github.workspace }}\.ccache
|
||||
key: ccache-${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.preset }}-${{ needs.setup-environment.outputs.vendorsha }}
|
||||
- name: Build target "${{ matrix.preset }}"
|
||||
run: |
|
||||
Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
|
||||
Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation -DevCmdArguments '-arch=x64 -no_logo'
|
||||
cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }} --install-prefix "$((pwd).Path)\dist\${{ matrix.os }}-${{ matrix.arch }}"
|
||||
cmake --build --preset "${{ matrix.preset }}" -- -l $([Environment]::ProcessorCount)
|
||||
cmake --install build --component "${{ startsWith(matrix.preset, 'MLX ') && 'MLX' || startsWith(matrix.preset, 'CUDA ') && 'CUDA' || startsWith(matrix.preset, 'ROCm ') && 'HIP' || startsWith(matrix.preset, 'Vulkan') && 'Vulkan' || 'CPU' }}" --strip
|
||||
if ('${{ matrix.preset }}'.StartsWith('MLX ')) { cmake --install build --component MLX_VENDOR }
|
||||
Remove-Item -Path dist\lib\ollama\rocm\rocblas\library\*gfx906* -ErrorAction SilentlyContinue
|
||||
env:
|
||||
CMAKE_GENERATOR: Ninja
|
||||
- name: Log build results
|
||||
run: |
|
||||
gci -path .\dist -Recurse -File | ForEach-Object { get-filehash -path $_.FullName -Algorithm SHA256 } | format-list
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: depends-${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.preset }}
|
||||
path: dist\*
|
||||
|
||||
windows-build:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [windows]
|
||||
arch: [amd64, arm64]
|
||||
include:
|
||||
- os: windows
|
||||
arch: amd64
|
||||
llvmarch: x86_64
|
||||
- os: windows
|
||||
arch: arm64
|
||||
llvmarch: aarch64
|
||||
runs-on: ${{ matrix.arch == 'arm64' && format('{0}-{1}', matrix.os, matrix.arch) || matrix.os }}
|
||||
environment: release
|
||||
needs: [setup-environment]
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
steps:
|
||||
- name: Install ARM64 system dependencies
|
||||
if: matrix.arch == 'arm64'
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
Set-ExecutionPolicy Bypass -Scope Process -Force
|
||||
[System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072
|
||||
iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))
|
||||
echo "C:\ProgramData\chocolatey\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
|
||||
Invoke-WebRequest -Uri https://aka.ms/vs/17/release/vc_redist.arm64.exe -OutFile "${{ runner.temp }}\vc_redist.arm64.exe"
|
||||
Start-Process -FilePath "${{ runner.temp }}\vc_redist.arm64.exe" -ArgumentList @("/install", "/quiet", "/norestart") -NoNewWindow -Wait
|
||||
|
||||
choco install -y --no-progress git gzip
|
||||
echo "C:\Program Files\Git\cmd" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
- name: Install clang and gcc-compat
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
Set-ExecutionPolicy Bypass -Scope Process -Force
|
||||
Invoke-WebRequest -Uri "https://github.com/mstorsjo/llvm-mingw/releases/download/20240619/llvm-mingw-20240619-ucrt-${{ matrix.llvmarch }}.zip" -OutFile "${{ runner.temp }}\llvm-mingw-ucrt.zip"
|
||||
Expand-Archive -Path ${{ runner.temp }}\llvm-mingw-ucrt.zip -DestinationPath "C:\Program Files\"
|
||||
$installPath=(Resolve-Path -Path "C:\Program Files\llvm-mingw-*-ucrt*").path
|
||||
echo "$installPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
Makefile.sync
|
||||
- name: Verify gcc is actually clang
|
||||
run: |
|
||||
$ErrorActionPreference='Continue'
|
||||
$version=& gcc -v 2>&1
|
||||
$version=$version -join "`n"
|
||||
echo "gcc is $version"
|
||||
if ($version -notmatch 'clang') {
|
||||
echo "ERROR: GCC must be clang for proper utf16 handling"
|
||||
exit 1
|
||||
}
|
||||
$ErrorActionPreference='Stop'
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "20"
|
||||
- run: |
|
||||
./scripts/build_windows ollama app
|
||||
- name: Log build results
|
||||
run: |
|
||||
gci -path .\dist -Recurse -File | ForEach-Object { get-filehash -path $_.FullName -Algorithm SHA256 } | format-list
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: build-${{ matrix.os }}-${{ matrix.arch }}
|
||||
path: |
|
||||
dist\*
|
||||
|
||||
windows-app:
|
||||
runs-on: windows
|
||||
environment: release
|
||||
needs: [windows-build, windows-depends]
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
KEY_CONTAINER: ${{ vars.KEY_CONTAINER }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: google-github-actions/auth@v2
|
||||
with:
|
||||
project_id: ollama
|
||||
credentials_json: ${{ secrets.GOOGLE_SIGNING_CREDENTIALS }}
|
||||
- run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
Invoke-WebRequest -Uri "https://go.microsoft.com/fwlink/p/?LinkId=323507" -OutFile "${{ runner.temp }}\sdksetup.exe"
|
||||
Start-Process "${{ runner.temp }}\sdksetup.exe" -ArgumentList @("/q") -NoNewWindow -Wait
|
||||
|
||||
Invoke-WebRequest -Uri "https://github.com/GoogleCloudPlatform/kms-integrations/releases/download/cng-v1.0/kmscng-1.0-windows-amd64.zip" -OutFile "${{ runner.temp }}\plugin.zip"
|
||||
Expand-Archive -Path "${{ runner.temp }}\plugin.zip" -DestinationPath "${{ runner.temp }}\plugin\"
|
||||
& "${{ runner.temp }}\plugin\*\kmscng.msi" /quiet
|
||||
|
||||
echo "${{ vars.OLLAMA_CERT }}" >ollama_inc.crt
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
Makefile.sync
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: depends-windows*
|
||||
path: dist
|
||||
merge-multiple: true
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: build-windows*
|
||||
path: dist
|
||||
merge-multiple: true
|
||||
- name: Log dist contents after download
|
||||
run: |
|
||||
gci -path .\dist -recurse
|
||||
- run: |
|
||||
./scripts/build_windows.ps1 deps sign installer zip
|
||||
- name: Log contents after build
|
||||
run: |
|
||||
gci -path .\dist -Recurse -File | ForEach-Object { get-filehash -path $_.FullName -Algorithm SHA256 } | format-list
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: bundles-windows
|
||||
path: |
|
||||
dist/*.zip
|
||||
dist/*.ps1
|
||||
dist/OllamaSetup.exe
|
||||
|
||||
# Pre-build each Dockerfile stage on its own runner in parallel and push the
|
||||
# resulting layers to a per-stage registry cache. The downstream
|
||||
# docker-build-push job then assembles cache-hit-only.
|
||||
linux-depends:
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- arch: amd64
|
||||
target: cpu
|
||||
- arch: amd64
|
||||
target: cuda-12
|
||||
- arch: amd64
|
||||
target: cuda-13
|
||||
- arch: amd64
|
||||
target: mlx
|
||||
- arch: amd64
|
||||
target: rocm-7
|
||||
- arch: amd64
|
||||
target: vulkan
|
||||
- arch: arm64
|
||||
target: cpu
|
||||
- arch: arm64
|
||||
target: cuda-12
|
||||
- arch: arm64
|
||||
target: cuda-13
|
||||
- arch: arm64
|
||||
target: jetpack-5
|
||||
- arch: arm64
|
||||
target: jetpack-6
|
||||
runs-on: ${{ matrix.arch == 'arm64' && 'linux-arm64' || 'linux' }}
|
||||
environment: release
|
||||
needs: setup-environment
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
- uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ vars.DOCKER_USER }}
|
||||
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
|
||||
# Increase swap to handle momentary spikes in RAM from NVCC compiles
|
||||
- if: matrix.target == 'mlx'
|
||||
name: Increase Linux swap to 200 GB
|
||||
shell: bash
|
||||
run: |
|
||||
set -e
|
||||
SWAP_PATH=/swapfile-mlx
|
||||
SWAP_SIZE_GB=200
|
||||
if [ -f "$SWAP_PATH" ]; then
|
||||
sudo swapoff "$SWAP_PATH" 2>/dev/null || true
|
||||
sudo rm -f "$SWAP_PATH"
|
||||
fi
|
||||
if ! sudo fallocate -l ${SWAP_SIZE_GB}G "$SWAP_PATH" 2>/dev/null; then
|
||||
echo "fallocate unsupported, falling back to dd"
|
||||
sudo dd if=/dev/zero of="$SWAP_PATH" bs=1M count=$((SWAP_SIZE_GB * 1024))
|
||||
fi
|
||||
sudo chmod 600 "$SWAP_PATH"
|
||||
sudo mkswap "$SWAP_PATH"
|
||||
sudo swapon "$SWAP_PATH"
|
||||
swapon --show
|
||||
free -h
|
||||
- uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
platforms: linux/${{ matrix.arch }}
|
||||
target: ${{ matrix.target }}
|
||||
provenance: false
|
||||
sbom: false
|
||||
build-args: |
|
||||
CGO_CFLAGS=${{ env.CGO_CFLAGS }}
|
||||
CGO_CXXFLAGS=${{ env.CGO_CXXFLAGS }}
|
||||
GOFLAGS=${{ env.GOFLAGS }}
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
OLLAMA_MLX_BUILD_JOBS=16
|
||||
OLLAMA_MLX_NVCC_THREADS=6
|
||||
cache-from: |
|
||||
type=registry,ref=ollama/release:cache-${{ matrix.arch }}-${{ matrix.target }}
|
||||
type=registry,ref=${{ vars.DOCKER_REPO }}:latest
|
||||
cache-to: type=registry,ref=ollama/release:cache-${{ matrix.arch }}-${{ matrix.target }},mode=max
|
||||
|
||||
# Build each Docker variant (OS, arch, and flavor) separately. Using QEMU is unreliable and slower.
|
||||
# Heavy stages were pre-built by linux-depends; this job is cache-hit-only for those layers
|
||||
# and just assembles, runs the Go build, and pushes the final image.
|
||||
docker-build-push:
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- os: linux
|
||||
arch: arm64
|
||||
build-args: |
|
||||
CGO_CFLAGS
|
||||
CGO_CXXFLAGS
|
||||
GOFLAGS
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
OLLAMA_MLX_BUILD_JOBS=16
|
||||
OLLAMA_MLX_NVCC_THREADS=6
|
||||
cache-from: |
|
||||
type=registry,ref=${{ vars.DOCKER_REPO }}:latest
|
||||
type=registry,ref=ollama/release:cache-arm64-cpu
|
||||
type=registry,ref=ollama/release:cache-arm64-cuda-12
|
||||
type=registry,ref=ollama/release:cache-arm64-cuda-13
|
||||
type=registry,ref=ollama/release:cache-arm64-jetpack-5
|
||||
type=registry,ref=ollama/release:cache-arm64-jetpack-6
|
||||
- os: linux
|
||||
arch: amd64
|
||||
build-args: |
|
||||
CGO_CFLAGS
|
||||
CGO_CXXFLAGS
|
||||
GOFLAGS
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
OLLAMA_MLX_BUILD_JOBS=16
|
||||
OLLAMA_MLX_NVCC_THREADS=6
|
||||
cache-from: |
|
||||
type=registry,ref=${{ vars.DOCKER_REPO }}:latest
|
||||
type=registry,ref=ollama/release:cache-amd64-cpu
|
||||
type=registry,ref=ollama/release:cache-amd64-cuda-12
|
||||
type=registry,ref=ollama/release:cache-amd64-cuda-13
|
||||
type=registry,ref=ollama/release:cache-amd64-mlx
|
||||
type=registry,ref=ollama/release:cache-amd64-vulkan
|
||||
- os: linux
|
||||
arch: amd64
|
||||
suffix: '-rocm'
|
||||
build-args: |
|
||||
CGO_CFLAGS
|
||||
CGO_CXXFLAGS
|
||||
GOFLAGS
|
||||
FLAVOR=rocm
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
OLLAMA_MLX_BUILD_JOBS=16
|
||||
OLLAMA_MLX_NVCC_THREADS=6
|
||||
cache-from: |
|
||||
type=registry,ref=${{ vars.DOCKER_REPO }}:latest
|
||||
type=registry,ref=ollama/release:cache-amd64-cpu
|
||||
type=registry,ref=ollama/release:cache-amd64-rocm-7
|
||||
runs-on: ${{ matrix.arch == 'arm64' && format('{0}-{1}', matrix.os, matrix.arch) || matrix.os }}
|
||||
environment: release
|
||||
needs: [setup-environment, linux-depends]
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
- uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ vars.DOCKER_USER }}
|
||||
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
|
||||
- id: build-push
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
platforms: ${{ matrix.os }}/${{ matrix.arch }}
|
||||
provenance: false
|
||||
sbom: false
|
||||
build-args: ${{ matrix.build-args }}
|
||||
outputs: type=image,name=${{ vars.DOCKER_REPO }},push-by-digest=true,name-canonical=true,push=true
|
||||
cache-from: ${{ matrix.cache-from }}
|
||||
cache-to: type=inline
|
||||
- run: |
|
||||
mkdir -p ${{ matrix.os }}-${{ matrix.arch }}
|
||||
echo "${{ steps.build-push.outputs.digest }}" >${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.suffix }}.txt
|
||||
working-directory: ${{ runner.temp }}
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: digest-${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.suffix }}
|
||||
path: |
|
||||
${{ runner.temp }}/${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.suffix }}.txt
|
||||
# Re-run buildx with --target archive against buildkit's local cache to
|
||||
# extract the release directory layout. All upstream stages were just
|
||||
# built above, so this is a cache-hit-only pass that just writes files.
|
||||
- uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
platforms: ${{ matrix.os }}/${{ matrix.arch }}
|
||||
target: archive
|
||||
provenance: false
|
||||
sbom: false
|
||||
build-args: ${{ matrix.build-args }}
|
||||
outputs: type=local,dest=dist/${{ matrix.os }}-${{ matrix.arch }}
|
||||
cache-from: ${{ matrix.cache-from }}
|
||||
- name: Deduplicate CUDA libraries
|
||||
run: |
|
||||
./scripts/deduplicate_cuda_libs.sh dist/${{ matrix.os }}-${{ matrix.arch }}
|
||||
- run: |
|
||||
for COMPONENT in bin/* lib/ollama/*; do
|
||||
case "$COMPONENT" in
|
||||
bin/ollama*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/*.so*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/cuda_v*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/vulkan*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/mlx*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}-mlx.tar.in ;;
|
||||
lib/ollama/include*) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/cuda_jetpack5) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}-jetpack5.tar.in ;;
|
||||
lib/ollama/cuda_jetpack6) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}-jetpack6.tar.in ;;
|
||||
lib/ollama/rocm) echo $COMPONENT >>ollama-${{ matrix.os }}-${{ matrix.arch }}-rocm.tar.in ;;
|
||||
esac
|
||||
done
|
||||
working-directory: dist/${{ matrix.os }}-${{ matrix.arch }}
|
||||
# rocm builds cpu + rocm libs for the container image, which
|
||||
# creates a CPU-only amd64 tarball that would collide with the full
|
||||
# bundle when the release job merges artifacts.
|
||||
- if: matrix.suffix == '-rocm'
|
||||
run: rm -f dist/${{ matrix.os }}-${{ matrix.arch }}/ollama-${{ matrix.os }}-${{ matrix.arch }}.tar.in
|
||||
- run: |
|
||||
echo "Manifests"
|
||||
for ARCHIVE in dist/${{ matrix.os }}-${{ matrix.arch }}/*.tar.in ; do
|
||||
echo $ARCHIVE
|
||||
cat $ARCHIVE
|
||||
done
|
||||
- run: |
|
||||
for ARCHIVE in dist/${{ matrix.os }}-${{ matrix.arch }}/*.tar.in; do
|
||||
tar c -C dist/${{ matrix.os }}-${{ matrix.arch }} -T $ARCHIVE --owner 0 --group 0 | zstd -19 -T0 >$(basename ${ARCHIVE//.*/}.tar.zst) &
|
||||
done
|
||||
wait
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: bundles-${{ matrix.os }}-${{ matrix.arch }}${{ matrix.suffix }}
|
||||
path: |
|
||||
*.tar.zst
|
||||
|
||||
# Merge Docker images for the same flavor into a single multi-arch manifest
|
||||
docker-merge-push:
|
||||
strategy:
|
||||
matrix:
|
||||
suffix: ['', '-rocm']
|
||||
runs-on: linux
|
||||
environment: release
|
||||
needs: [docker-build-push]
|
||||
steps:
|
||||
- uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ vars.DOCKER_USER }}
|
||||
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
|
||||
- id: metadata
|
||||
uses: docker/metadata-action@v4
|
||||
with:
|
||||
flavor: |
|
||||
latest=false
|
||||
suffix=${{ matrix.suffix }}
|
||||
images: |
|
||||
${{ vars.DOCKER_REPO }}
|
||||
tags: |
|
||||
type=ref,enable=true,priority=600,prefix=pr-,event=pr
|
||||
type=semver,pattern={{version}}
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: digest-*
|
||||
path: ${{ runner.temp }}
|
||||
merge-multiple: true
|
||||
- run: |
|
||||
docker buildx imagetools create $(echo '${{ steps.metadata.outputs.json }}' | jq -cr '.tags | map("-t", .) | join(" ")') $(cat *-${{ matrix.suffix }}.txt | xargs printf '${{ vars.DOCKER_REPO }}@%s ')
|
||||
docker buildx imagetools inspect ${{ vars.DOCKER_REPO }}:${{ steps.metadata.outputs.version }}
|
||||
working-directory: ${{ runner.temp }}
|
||||
|
||||
# Final release process
|
||||
release:
|
||||
runs-on: ubuntu-latest
|
||||
environment: release
|
||||
needs: [darwin-build, windows-app, docker-build-push]
|
||||
permissions:
|
||||
contents: write
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: bundles-*
|
||||
path: dist
|
||||
merge-multiple: true
|
||||
- name: Log dist contents
|
||||
run: |
|
||||
ls -l dist/
|
||||
- name: Copy install scripts to dist
|
||||
run: |
|
||||
cp scripts/install.sh dist/install.sh
|
||||
- name: Generate checksum file
|
||||
run: find . -type f -not -name 'sha256sum.txt' | xargs sha256sum | tee sha256sum.txt
|
||||
working-directory: dist
|
||||
- name: Create or update Release for tag
|
||||
run: |
|
||||
RELEASE_VERSION="$(echo ${GITHUB_REF_NAME} | cut -f1 -d-)"
|
||||
echo "Looking for existing release for ${RELEASE_VERSION}"
|
||||
OLD_TAG=$(gh release ls --json name,tagName | jq -r ".[] | select(.name == \"${RELEASE_VERSION}\") | .tagName")
|
||||
if [ -n "$OLD_TAG" ]; then
|
||||
echo "Updating release ${RELEASE_VERSION} to point to new tag ${GITHUB_REF_NAME}"
|
||||
gh release edit ${OLD_TAG} --tag ${GITHUB_REF_NAME}
|
||||
else
|
||||
echo "Creating new release ${RELEASE_VERSION} pointing to tag ${GITHUB_REF_NAME}"
|
||||
gh release create ${GITHUB_REF_NAME} \
|
||||
--title ${RELEASE_VERSION} \
|
||||
--draft \
|
||||
--generate-notes \
|
||||
--prerelease
|
||||
fi
|
||||
- name: Upload release artifacts
|
||||
run: |
|
||||
pids=()
|
||||
for payload in dist/*.txt dist/*.zip dist/*.tgz dist/*.tar.zst dist/*.exe dist/*.dmg dist/*.ps1 dist/*.sh ; do
|
||||
echo "Uploading $payload"
|
||||
gh release upload ${GITHUB_REF_NAME} $payload --clobber &
|
||||
pids+=($!)
|
||||
sleep 1
|
||||
done
|
||||
echo "Waiting for uploads to complete"
|
||||
failed=0
|
||||
for pid in "${pids[@]}"; do
|
||||
if ! wait $pid; then
|
||||
echo "::error::Upload failed (pid $pid)"
|
||||
failed=1
|
||||
fi
|
||||
done
|
||||
if [ $failed -ne 0 ]; then
|
||||
echo "One or more uploads failed"
|
||||
exit 1
|
||||
fi
|
||||
echo "done"
|
||||
22
.github/workflows/test-install.yaml
vendored
Normal file
22
.github/workflows/test-install.yaml
vendored
Normal file
@@ -0,0 +1,22 @@
|
||||
name: test-install
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'scripts/install.sh'
|
||||
- '.github/workflows/test-install.yaml'
|
||||
|
||||
jobs:
|
||||
test:
|
||||
strategy:
|
||||
matrix:
|
||||
os: [ubuntu-latest, macos-latest]
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Run install script
|
||||
run: sh ./scripts/install.sh
|
||||
env:
|
||||
OLLAMA_NO_START: 1 # do not start app
|
||||
- name: Verify ollama is available
|
||||
run: ollama --version
|
||||
305
.github/workflows/test.yaml
vendored
Normal file
305
.github/workflows/test.yaml
vendored
Normal file
@@ -0,0 +1,305 @@
|
||||
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 }}
|
||||
app_changed: ${{ steps.changes.outputs.app_changed }}
|
||||
vendorsha: ${{ steps.changes.outputs.vendorsha }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
- id: changes
|
||||
run: |
|
||||
changed() {
|
||||
local BASE=${{ 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/**/*' '.github/**/*') | tee -a $GITHUB_OUTPUT
|
||||
echo app_changed=$(changed 'app/**' 'app/**/*') | tee -a $GITHUB_OUTPUT
|
||||
echo vendorsha=$(make -f Makefile.sync print-base) | tee -a $GITHUB_OUTPUT
|
||||
|
||||
linux:
|
||||
needs: [changes]
|
||||
if: needs.changes.outputs.changed == 'True'
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- preset: CPU
|
||||
- preset: CUDA
|
||||
container: nvidia/cuda:13.0.0-devel-ubuntu22.04
|
||||
flags: '-DCMAKE_CUDA_ARCHITECTURES=87'
|
||||
- preset: ROCm
|
||||
container: rocm/dev-ubuntu-22.04:7.2.1
|
||||
extra-packages: rocm-libs
|
||||
flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_PREFIX_PATH=/opt/rocm'
|
||||
- preset: Vulkan
|
||||
container: ubuntu:22.04
|
||||
extra-packages: >
|
||||
mesa-vulkan-drivers vulkan-tools
|
||||
libvulkan1 libvulkan-dev
|
||||
vulkan-sdk cmake ccache g++ make
|
||||
- preset: 'MLX CUDA 13'
|
||||
container: nvidia/cuda:13.0.0-devel-ubuntu22.04
|
||||
extra-packages: libcudnn9-dev-cuda-13 libopenblas-dev liblapack-dev liblapacke-dev git curl
|
||||
flags: '-DCMAKE_CUDA_ARCHITECTURES=87 -DMLX_CUDA_ARCHITECTURES=80-virtual -DBLAS_INCLUDE_DIRS=/usr/include/x86_64-linux-gnu -DLAPACK_INCLUDE_DIRS=/usr/include/x86_64-linux-gnu'
|
||||
install-go: true
|
||||
runs-on: linux
|
||||
container: ${{ matrix.container }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- run: |
|
||||
[ -n "${{ matrix.container }}" ] || sudo=sudo
|
||||
$sudo apt-get update
|
||||
# Add LunarG Vulkan SDK apt repo for Ubuntu 22.04
|
||||
if [ "${{ matrix.preset }}" = "Vulkan" ]; then
|
||||
$sudo apt-get install -y --no-install-recommends wget gnupg ca-certificates software-properties-common
|
||||
wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | $sudo gpg --dearmor -o /usr/share/keyrings/lunarg-archive-keyring.gpg
|
||||
# Use signed-by to bind the repo to the installed keyring to avoid NO_PUBKEY
|
||||
echo "deb [signed-by=/usr/share/keyrings/lunarg-archive-keyring.gpg] https://packages.lunarg.com/vulkan/1.4.313 jammy main" | $sudo tee /etc/apt/sources.list.d/lunarg-vulkan-1.4.313-jammy.list > /dev/null
|
||||
$sudo apt-get update
|
||||
fi
|
||||
$sudo apt-get install -y cmake ccache ${{ matrix.extra-packages }}
|
||||
# MLX requires CMake 3.25+, install from official releases
|
||||
if [ "${{ matrix.preset }}" = "MLX CUDA 13" ]; then
|
||||
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.31.2/cmake-3.31.2-linux-$(uname -m).tar.gz | $sudo tar xz -C /usr/local --strip-components 1
|
||||
fi
|
||||
# Export VULKAN_SDK if provided by LunarG package (defensive)
|
||||
if [ -d "/usr/lib/x86_64-linux-gnu/vulkan" ] && [ "${{ matrix.preset }}" = "Vulkan" ]; then
|
||||
echo "VULKAN_SDK=/usr" >> $GITHUB_ENV
|
||||
fi
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
- if: matrix.install-go
|
||||
name: Install Go
|
||||
run: |
|
||||
GO_VERSION=$(awk '/^go / { print $2 }' go.mod)
|
||||
curl -fsSL "https://golang.org/dl/go${GO_VERSION}.linux-$(dpkg --print-architecture).tar.gz" | tar xz -C /usr/local
|
||||
echo "/usr/local/go/bin" >> $GITHUB_PATH
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
path: /github/home/.cache/ccache
|
||||
key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
|
||||
- run: |
|
||||
cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
|
||||
cmake --build --preset "${{ matrix.preset }}" -- -l $(nproc)
|
||||
|
||||
windows:
|
||||
needs: [changes]
|
||||
if: needs.changes.outputs.changed == 'True'
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- preset: CPU
|
||||
- preset: CUDA
|
||||
install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
|
||||
flags: '-DCMAKE_CUDA_ARCHITECTURES=80'
|
||||
cuda-components:
|
||||
- '"cudart"'
|
||||
- '"nvcc"'
|
||||
- '"cublas"'
|
||||
- '"cublas_dev"'
|
||||
- '"crt"'
|
||||
- '"nvvm"'
|
||||
- '"nvptxcompiler"'
|
||||
cuda-version: '13.0'
|
||||
- preset: ROCm
|
||||
install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
|
||||
flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
|
||||
- preset: Vulkan
|
||||
install: https://sdk.lunarg.com/sdk/download/1.4.321.1/windows/vulkansdk-windows-X64-1.4.321.1.exe
|
||||
- preset: 'MLX CUDA 13'
|
||||
install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
|
||||
cudnn-install: https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.18.1.3_cuda13-archive.zip
|
||||
flags: '-DCMAKE_CUDA_ARCHITECTURES=80 -DMLX_CUDA_ARCHITECTURES=80-virtual'
|
||||
cuda-components:
|
||||
- '"cudart"'
|
||||
- '"nvcc"'
|
||||
- '"cublas"'
|
||||
- '"cublas_dev"'
|
||||
- '"cufft"'
|
||||
- '"cufft_dev"'
|
||||
- '"nvrtc"'
|
||||
- '"nvrtc_dev"'
|
||||
- '"crt"'
|
||||
- '"nvvm"'
|
||||
- '"nvptxcompiler"'
|
||||
cuda-version: '13.0'
|
||||
runs-on: windows
|
||||
steps:
|
||||
- run: |
|
||||
choco install -y --no-progress ccache ninja
|
||||
if (Get-Command ccache -ErrorAction SilentlyContinue) {
|
||||
ccache -o cache_dir=${{ github.workspace }}\.ccache
|
||||
}
|
||||
- if: matrix.preset == 'CUDA' || matrix.preset == 'ROCm' || matrix.preset == 'Vulkan' || matrix.preset == 'MLX CUDA 13'
|
||||
id: cache-install
|
||||
uses: actions/cache/restore@v4
|
||||
with:
|
||||
path: |
|
||||
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
|
||||
C:\Program Files\AMD\ROCm
|
||||
C:\VulkanSDK
|
||||
C:\Program Files\NVIDIA\CUDNN
|
||||
key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
|
||||
- if: matrix.preset == 'CUDA' || matrix.preset == 'MLX CUDA 13'
|
||||
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"
|
||||
$subpackages = @(${{ join(matrix.cuda-components, ', ') }}) | Foreach-Object {"${_}_${{ matrix.cuda-version }}"}
|
||||
Start-Process -FilePath .\install.exe -ArgumentList (@("-s") + $subpackages) -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 $env:GITHUB_ENV -Append
|
||||
echo "HIPCXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "HIP_PLATFORM=amd" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CMAKE_PREFIX_PATH=$hipPath" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
- if: matrix.preset == 'Vulkan'
|
||||
name: Install Vulkan ${{ 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 "-c","--am","--al","in" -NoNewWindow -Wait
|
||||
}
|
||||
|
||||
$vulkanPath = (Resolve-Path "C:\VulkanSDK\*").path
|
||||
echo "$vulkanPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
echo "VULKAN_SDK=$vulkanPath" >> $env:GITHUB_ENV
|
||||
- if: matrix.preset == 'MLX CUDA 13'
|
||||
name: Install cuDNN for MLX
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
$cudnnRoot = "C:\Program Files\NVIDIA\CUDNN"
|
||||
if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
|
||||
Invoke-WebRequest -Uri "${{ matrix.cudnn-install }}" -OutFile "cudnn.zip"
|
||||
Expand-Archive -Path cudnn.zip -DestinationPath cudnn-extracted
|
||||
$cudnnDir = (Get-ChildItem -Path cudnn-extracted -Directory)[0].FullName
|
||||
New-Item -ItemType Directory -Force -Path $cudnnRoot
|
||||
Copy-Item -Path "$cudnnDir\*" -Destination "$cudnnRoot\" -Recurse
|
||||
}
|
||||
|
||||
echo "CUDNN_ROOT_DIR=$cudnnRoot" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CUDNN_INCLUDE_PATH=$cudnnRoot\include" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "CUDNN_LIBRARY_PATH=$cudnnRoot\lib\x64" | Out-File -FilePath $env:GITHUB_ENV -Append
|
||||
echo "$cudnnRoot\bin\x64" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -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
|
||||
C:\VulkanSDK
|
||||
C:\Program Files\NVIDIA\CUDNN
|
||||
key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ github.workspace }}\.ccache
|
||||
key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
|
||||
- run: |
|
||||
Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
|
||||
Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation -DevCmdArguments '-arch=x64 -no_logo'
|
||||
cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
|
||||
cmake --build --preset "${{ matrix.preset }}" -- -l $([Environment]::ProcessorCount)
|
||||
env:
|
||||
CMAKE_GENERATOR: Ninja
|
||||
|
||||
go_mod_tidy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: check that 'go mod tidy' is clean
|
||||
run: go mod tidy --diff || (echo "Please run 'go mod tidy'." && exit 1)
|
||||
|
||||
test:
|
||||
needs: [changes]
|
||||
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'
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
Makefile.sync
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '20'
|
||||
- name: Install UI dependencies
|
||||
working-directory: ./app/ui/app
|
||||
run: npm ci
|
||||
- name: Install tscriptify
|
||||
run: |
|
||||
go install github.com/tkrajina/typescriptify-golang-structs/tscriptify@latest
|
||||
- name: Run UI tests
|
||||
if: ${{ startsWith(matrix.os, 'ubuntu') }}
|
||||
working-directory: ./app/ui/app
|
||||
run: npm test
|
||||
- name: Run go generate
|
||||
run: go generate ./...
|
||||
|
||||
- name: go test
|
||||
if: always()
|
||||
run: go test -count=1 -benchtime=1x ./...
|
||||
|
||||
- name: go test app with live updater tag
|
||||
if: ${{ needs.changes.outputs.app_changed == 'True' && contains(fromJSON('["macos-latest","windows-latest"]'), matrix.os) }}
|
||||
run: go test -count=1 -tags updater_live ./app/...
|
||||
|
||||
- uses: golangci/golangci-lint-action@v9
|
||||
with:
|
||||
only-new-issues: true
|
||||
|
||||
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 apply-patches sync
|
||||
git diff --compact-summary --exit-code
|
||||
Reference in New Issue
Block a user