llama-server followups (#16353)
* llama-server followups Misc fixes for #16031 - Add back dropped ROCm build flag for multi-GPU support on windows - Fix amdhip64_*.dll version detection for "latest" selection - Fix embeddings API for consistent normalize behavior with prior versions * ci: set up for automated llama.cpp update testing * reduce batch for fa-disabled, and constrained vram * mlx: fix v3 load bug on m5 Imagegen was incorrectly loading v3 first. This DRYs out the loading code so imagegen gets the same new v4/v3 selection logic. * fix reload bug on embedding models * bump version * steer user how to enable iGPU when disabled
This commit is contained in:
Daniel Hiltgen
@@ -0,0 +1,596 @@
|
||||
name: test-llamacpp-update
|
||||
|
||||
# PR validation artifacts from this workflow are intentionally unsigned and not
|
||||
# notarized. They are for llama.cpp update testing only and must not be
|
||||
# published as release artifacts.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'LLAMA_CPP_VERSION'
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
env:
|
||||
CGO_CFLAGS: '-O3'
|
||||
CGO_CXXFLAGS: '-O3'
|
||||
|
||||
jobs:
|
||||
setup-environment:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
GOFLAGS: ${{ steps.goflags.outputs.GOFLAGS }}
|
||||
VERSION: ${{ steps.goflags.outputs.VERSION }}
|
||||
vendorsha: ${{ steps.goflags.outputs.vendorsha }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set environment
|
||||
id: goflags
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
VERSION="0.0.0-llamacpp-${GITHUB_SHA::7}"
|
||||
{
|
||||
echo "GOFLAGS='-ldflags=-w -s \"-X=github.com/ollama/ollama/version.Version=${VERSION}\" \"-X=github.com/ollama/ollama/server.mode=release\"'"
|
||||
echo "VERSION=${VERSION}"
|
||||
echo "vendorsha=$(cat LLAMA_CPP_VERSION)-$(cat MLX_VERSION)-$(cat MLX_C_VERSION)"
|
||||
} >>"${GITHUB_OUTPUT}"
|
||||
|
||||
darwin-build:
|
||||
runs-on: macos-26-xlarge
|
||||
needs: setup-environment
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
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
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
LLAMA_CPP_VERSION
|
||||
MLX_VERSION
|
||||
MLX_C_VERSION
|
||||
- name: Build unsigned Darwin runtime
|
||||
run: ./scripts/build_darwin.sh build package
|
||||
- name: Log build results
|
||||
run: ls -l dist/
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-darwin.tgz
|
||||
path: dist/ollama-darwin.tgz
|
||||
compression-level: 0
|
||||
|
||||
# Build payload export stages independently and combine the exported
|
||||
# filesystem artifacts below. This preserves parallelism without Docker
|
||||
# registry credentials or oversized GitHub layer caches.
|
||||
linux-payloads:
|
||||
runs-on: ${{ matrix.arch == 'arm64' && 'linux-arm64' || 'linux' }}
|
||||
needs: setup-environment
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- arch: amd64
|
||||
target: publish-llama-server-cpu
|
||||
payload: cpu
|
||||
- arch: amd64
|
||||
target: publish-llama-server-cuda_v12
|
||||
payload: cuda_v12
|
||||
- arch: amd64
|
||||
target: publish-llama-server-cuda_v13
|
||||
payload: cuda_v13
|
||||
- arch: amd64
|
||||
target: publish-llama-server-rocm_v7_2
|
||||
payload: rocm_v7_2
|
||||
- arch: amd64
|
||||
target: publish-llama-server-vulkan
|
||||
payload: vulkan
|
||||
- arch: arm64
|
||||
target: publish-llama-server-cpu
|
||||
payload: cpu
|
||||
- arch: arm64
|
||||
target: publish-llama-server-cuda_v12
|
||||
payload: cuda_v12
|
||||
- arch: arm64
|
||||
target: publish-llama-server-cuda_v13
|
||||
payload: cuda_v13
|
||||
- arch: arm64
|
||||
target: publish-llama-server-cuda_jetpack5
|
||||
payload: cuda_jetpack5
|
||||
- arch: arm64
|
||||
target: publish-llama-server-cuda_jetpack6
|
||||
payload: cuda_jetpack6
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
- uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
platforms: linux/${{ matrix.arch }}
|
||||
target: ${{ matrix.target }}
|
||||
provenance: false
|
||||
sbom: false
|
||||
build-args: |
|
||||
GOFLAGS=${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
CGO_CFLAGS=${{ env.CGO_CFLAGS }}
|
||||
CGO_CXXFLAGS=${{ env.CGO_CXXFLAGS }}
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
APT_PORTS_MIRROR=http://azure.ports.ubuntu.com/ubuntu-ports
|
||||
outputs: type=local,dest=${{ runner.temp }}/payload
|
||||
- name: Pack Linux payload
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
tar -C "${{ runner.temp }}/payload" -cf - . | zstd -9 -T0 >"${{ runner.temp }}/linux-payload-${{ matrix.arch }}-${{ matrix.payload }}.tar.zst"
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: linux-payload-${{ matrix.arch }}-${{ matrix.payload }}
|
||||
path: ${{ runner.temp }}/linux-payload-${{ matrix.arch }}-${{ matrix.payload }}.tar.zst
|
||||
compression-level: 0
|
||||
|
||||
linux-go:
|
||||
runs-on: ${{ matrix.arch == 'arm64' && 'linux-arm64' || 'linux' }}
|
||||
needs: setup-environment
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
arch: [amd64, arm64]
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: docker/setup-buildx-action@v3
|
||||
- uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: .
|
||||
platforms: linux/${{ matrix.arch }}
|
||||
target: publish-go
|
||||
provenance: false
|
||||
sbom: false
|
||||
build-args: |
|
||||
GOFLAGS=${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
CGO_CFLAGS=${{ env.CGO_CFLAGS }}
|
||||
CGO_CXXFLAGS=${{ env.CGO_CXXFLAGS }}
|
||||
APT_MIRROR=http://azure.archive.ubuntu.com/ubuntu
|
||||
APT_PORTS_MIRROR=http://azure.ports.ubuntu.com/ubuntu-ports
|
||||
outputs: type=local,dest=${{ runner.temp }}/payload
|
||||
- name: Pack Linux Go payload
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
tar -C "${{ runner.temp }}/payload" -cf - . | zstd -9 -T0 >"${{ runner.temp }}/linux-payload-${{ matrix.arch }}-go.tar.zst"
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: linux-payload-${{ matrix.arch }}-go
|
||||
path: ${{ runner.temp }}/linux-payload-${{ matrix.arch }}-go.tar.zst
|
||||
compression-level: 0
|
||||
|
||||
# MLX payloads are intentionally excluded from this workflow; the Dockerfile
|
||||
# still exposes publish-mlx for a separate MLX-specific workflow.
|
||||
linux-bundles:
|
||||
runs-on: ${{ matrix.arch == 'arm64' && 'linux-arm64' || 'linux' }}
|
||||
needs: [linux-payloads, linux-go]
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
arch: [amd64, arm64]
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: linux-payload-${{ matrix.arch }}-*
|
||||
path: ${{ runner.temp }}/payloads
|
||||
merge-multiple: true
|
||||
- name: Assemble Linux payload tree
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
src="${{ runner.temp }}/payloads"
|
||||
arch="${{ matrix.arch }}"
|
||||
dest="dist/linux-${arch}"
|
||||
copy_payload() {
|
||||
local name="$1"
|
||||
local payload="${src}/linux-payload-${arch}-${name}.tar.zst"
|
||||
if [ ! -f "${payload}" ]; then
|
||||
echo "missing payload ${payload}"
|
||||
exit 1
|
||||
fi
|
||||
zstd -d <"${payload}" | tar -C "${dest}" -xf -
|
||||
}
|
||||
|
||||
mkdir -p "${dest}"
|
||||
copy_payload go
|
||||
copy_payload cpu
|
||||
copy_payload cuda_v12
|
||||
copy_payload cuda_v13
|
||||
if [ "${arch}" = "amd64" ]; then
|
||||
copy_payload vulkan
|
||||
copy_payload rocm_v7_2
|
||||
else
|
||||
copy_payload cuda_jetpack5
|
||||
copy_payload cuda_jetpack6
|
||||
fi
|
||||
|
||||
./scripts/deduplicate_cuda_libs.sh "${dest}"
|
||||
- name: Verify Linux build payloads
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
base="dist/linux-${{ matrix.arch }}"
|
||||
for payload in \
|
||||
"${base}/bin/ollama" \
|
||||
"${base}/lib/ollama/llama-server"
|
||||
do
|
||||
[ -f "${payload}" ] || { echo "missing ${payload}"; exit 1; }
|
||||
done
|
||||
- name: Create archive input lists
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for COMPONENT in bin/* lib/ollama/*; do
|
||||
case "${COMPONENT}" in
|
||||
bin/ollama*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/*.so*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/llama-server*|lib/ollama/llama-quantize*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/cuda_v*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/vulkan*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}.tar.in ;;
|
||||
lib/ollama/mlx*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}-mlx.tar.in ;;
|
||||
lib/ollama/include*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}-mlx.tar.in ;;
|
||||
lib/ollama/cuda_jetpack5) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}-jetpack5.tar.in ;;
|
||||
lib/ollama/cuda_jetpack6) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}-jetpack6.tar.in ;;
|
||||
lib/ollama/rocm_v*) echo "${COMPONENT}" >>ollama-linux-${{ matrix.arch }}-rocm.tar.in ;;
|
||||
esac
|
||||
done
|
||||
working-directory: dist/linux-${{ matrix.arch }}
|
||||
- name: Log archive input lists
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for ARCHIVE in dist/linux-${{ matrix.arch }}/*.tar.in; do
|
||||
echo "${ARCHIVE}"
|
||||
cat "${ARCHIVE}"
|
||||
done
|
||||
- name: Create Linux archives
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for ARCHIVE in dist/linux-${{ matrix.arch }}/*.tar.in; do
|
||||
tar c -C dist/linux-${{ matrix.arch }} -T "${ARCHIVE}" --owner 0 --group 0 | zstd -19 -T0 >"$(basename "${ARCHIVE//.*/}.tar.zst")" &
|
||||
done
|
||||
wait
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-linux-${{ matrix.arch }}.tar.zst
|
||||
path: ollama-linux-${{ matrix.arch }}.tar.zst
|
||||
compression-level: 0
|
||||
- if: matrix.arch == 'amd64'
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-linux-amd64-rocm.tar.zst
|
||||
path: ollama-linux-amd64-rocm.tar.zst
|
||||
compression-level: 0
|
||||
- if: matrix.arch == 'arm64'
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-linux-arm64-jetpack5.tar.zst
|
||||
path: ollama-linux-arm64-jetpack5.tar.zst
|
||||
compression-level: 0
|
||||
- if: matrix.arch == 'arm64'
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-linux-arm64-jetpack6.tar.zst
|
||||
path: ollama-linux-arm64-jetpack6.tar.zst
|
||||
compression-level: 0
|
||||
|
||||
windows-depends:
|
||||
needs: setup-environment
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [windows]
|
||||
arch: [amd64]
|
||||
preset: ['CPU']
|
||||
build-steps: ['cpu cpuArm64']
|
||||
include:
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'CUDA 12'
|
||||
build-steps: cuda12
|
||||
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'
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'CUDA 13'
|
||||
build-steps: cuda13
|
||||
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'
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: 'ROCm 7'
|
||||
build-steps: rocm7
|
||||
install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-26.Q1-Win11-For-HIP.exe
|
||||
rocm-version: '7.1'
|
||||
- os: windows
|
||||
arch: amd64
|
||||
preset: Vulkan
|
||||
build-steps: vulkan
|
||||
install: https://sdk.lunarg.com/sdk/download/1.4.321.1/windows/vulkansdk-windows-X64-1.4.321.1.exe
|
||||
runs-on: ${{ matrix.arch == 'arm64' && format('{0}-{1}', matrix.os, matrix.arch) || matrix.os }}
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
steps:
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
choco install -y --no-progress ccache ninja
|
||||
if (Get-Command ccache -ErrorAction SilentlyContinue) {
|
||||
ccache -o cache_dir=${{ github.workspace }}\.ccache
|
||||
}
|
||||
- if: matrix.preset == 'CPU'
|
||||
name: Install Windows ARM64 cross compiler
|
||||
run: |
|
||||
Invoke-WebRequest -Uri "https://github.com/mstorsjo/llvm-mingw/releases/download/20240619/llvm-mingw-20240619-ucrt-x86_64.zip" -OutFile "${{ runner.temp }}\llvm-mingw-ucrt.zip"
|
||||
Expand-Archive -Path ${{ runner.temp }}\llvm-mingw-ucrt.zip -DestinationPath "C:\Program Files\"
|
||||
$installPath=(Resolve-Path -Path "C:\Program Files\llvm-mingw-*-ucrt-x86_64").path
|
||||
if (!(Test-Path "$installPath\bin\aarch64-w64-mingw32-gcc.exe")) {
|
||||
throw "llvm-mingw x86_64 package is missing the aarch64 cross compiler"
|
||||
}
|
||||
- if: startsWith(matrix.preset, 'CUDA ') || startsWith(matrix.preset, 'ROCm ') || startsWith(matrix.preset, 'Vulkan')
|
||||
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
|
||||
key: ${{ matrix.install }}
|
||||
- if: startsWith(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"
|
||||
$subpackages = @(${{ 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
|
||||
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
|
||||
$vulkanRuntime = Join-Path $vulkanPath "Helpers\VulkanRT.exe"
|
||||
if (Test-Path $vulkanRuntime) {
|
||||
Start-Process -FilePath $vulkanRuntime -ArgumentList "/s" -NoNewWindow -Wait
|
||||
}
|
||||
echo "$vulkanPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
echo "VULKAN_SDK=$vulkanPath" >> $env:GITHUB_ENV
|
||||
- if: ${{ !cancelled() && matrix.preset != 'CPU' && 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
|
||||
key: ${{ matrix.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 Windows dependencies
|
||||
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'
|
||||
$steps = "${{ matrix.build-steps }}".Split(' ', [System.StringSplitOptions]::RemoveEmptyEntries)
|
||||
./scripts/build_windows.ps1 @steps
|
||||
env:
|
||||
CMAKE_GENERATOR: Ninja
|
||||
- name: Log build results
|
||||
run: |
|
||||
gci -path .\dist -Recurse -File | ForEach-Object { get-filehash -path $_.FullName -Algorithm SHA256 } | format-list
|
||||
- if: matrix.preset == 'CPU'
|
||||
name: Verify Windows CPU payloads
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for payload in \
|
||||
dist/windows-amd64/lib/ollama/llama-server.exe \
|
||||
dist/windows-arm64/lib/ollama/llama-server.exe
|
||||
do
|
||||
[ -f "$payload" ] || { echo "missing $payload"; exit 1; }
|
||||
done
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: depends-${{ matrix.os }}-${{ matrix.arch }}-${{ matrix.preset }}
|
||||
path: dist\*
|
||||
compression-level: 0
|
||||
|
||||
windows-build:
|
||||
runs-on: windows
|
||||
needs: setup-environment
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
steps:
|
||||
- name: Install clang and gcc-compat
|
||||
run: |
|
||||
$ErrorActionPreference = "Stop"
|
||||
Set-ExecutionPolicy Bypass -Scope Process -Force
|
||||
Invoke-WebRequest -Uri "https://github.com/mstorsjo/llvm-mingw/releases/download/20240619/llvm-mingw-20240619-ucrt-x86_64.zip" -OutFile "${{ runner.temp }}\llvm-mingw-ucrt.zip"
|
||||
Expand-Archive -Path ${{ runner.temp }}\llvm-mingw-ucrt.zip -DestinationPath "C:\Program Files\"
|
||||
$installPath=(Resolve-Path -Path "C:\Program Files\llvm-mingw-*-ucrt-x86_64").path
|
||||
echo "$installPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
if (!(Test-Path "$installPath\bin\aarch64-w64-mingw32-gcc.exe")) {
|
||||
throw "llvm-mingw x86_64 package is missing the aarch64 cross compiler"
|
||||
}
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
LLAMA_CPP_VERSION
|
||||
MLX_VERSION
|
||||
MLX_C_VERSION
|
||||
- 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
|
||||
}
|
||||
$ErrorActionPreference='Stop'
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "20"
|
||||
- name: Build Windows binaries and app launchers
|
||||
run: ./scripts/build_windows.ps1 ollama ollamaArm64 app appArm64
|
||||
- name: Verify Windows build payloads
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for payload in \
|
||||
dist/windows-amd64/ollama.exe \
|
||||
dist/windows-arm64/ollama.exe
|
||||
do
|
||||
[ -f "$payload" ] || { echo "missing $payload"; exit 1; }
|
||||
done
|
||||
- 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-windows-amd64
|
||||
path: dist\*
|
||||
compression-level: 0
|
||||
|
||||
windows-package:
|
||||
runs-on: windows
|
||||
needs: [setup-environment, windows-build, windows-depends]
|
||||
env:
|
||||
GOFLAGS: ${{ needs.setup-environment.outputs.GOFLAGS }}
|
||||
VERSION: ${{ needs.setup-environment.outputs.VERSION }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
with:
|
||||
go-version-file: go.mod
|
||||
cache-dependency-path: |
|
||||
go.sum
|
||||
LLAMA_CPP_VERSION
|
||||
MLX_VERSION
|
||||
MLX_C_VERSION
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: depends-windows*
|
||||
path: dist
|
||||
merge-multiple: true
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
pattern: build-windows*
|
||||
path: dist
|
||||
merge-multiple: true
|
||||
- name: Copy unsigned install script
|
||||
run: Copy-Item -Path .\scripts\install.ps1 -Destination .\dist\install.ps1 -ErrorAction Stop
|
||||
- name: Log dist contents after download
|
||||
run: gci -path .\dist -recurse
|
||||
- name: Verify Windows package inputs
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for payload in \
|
||||
dist/windows-amd64/ollama.exe \
|
||||
dist/windows-amd64/lib/ollama/llama-server.exe \
|
||||
dist/windows-arm64/ollama.exe \
|
||||
dist/windows-arm64/lib/ollama/llama-server.exe
|
||||
do
|
||||
[ -f "$payload" ] || { echo "missing $payload"; exit 1; }
|
||||
done
|
||||
- name: Build unsigned Windows installer and zips
|
||||
run: ./scripts/build_windows.ps1 deps installer zip
|
||||
- name: Log contents after build
|
||||
run: |
|
||||
gci -path .\dist -Recurse -File | ForEach-Object { get-filehash -path $_.FullName -Algorithm SHA256 } | format-list
|
||||
- name: Verify Windows package outputs
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for payload in \
|
||||
dist/ollama-windows-amd64.zip \
|
||||
dist/ollama-windows-arm64.zip \
|
||||
dist/ollama-windows-amd64-rocm.zip \
|
||||
dist/OllamaSetup.exe \
|
||||
dist/install.ps1
|
||||
do
|
||||
[ -f "$payload" ] || { echo "missing $payload"; exit 1; }
|
||||
done
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-windows-amd64.zip
|
||||
path: dist/ollama-windows-amd64.zip
|
||||
compression-level: 0
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-windows-arm64.zip
|
||||
path: dist/ollama-windows-arm64.zip
|
||||
compression-level: 0
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ollama-windows-amd64-rocm.zip
|
||||
path: dist/ollama-windows-amd64-rocm.zip
|
||||
compression-level: 0
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: OllamaSetup.exe
|
||||
path: dist/OllamaSetup.exe
|
||||
compression-level: 0
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: install.ps1
|
||||
path: dist/install.ps1
|
||||
compression-level: 0
|
||||
Reference in New Issue
Block a user