Files
lancedb/.github/workflows/pypi-publish.yml
Xuanwo a9e350c158 ci(python): build Windows release wheel on 8-core runner (#4264)
Since #4241 restored fat LTO / 1 codegen unit for the Windows wheel, the
`windows` job in PyPI Publish has been cancelled at its 90-minute
timeout on every run, including the v0.40.0-beta.6 and v0.40.0-beta.7
tags, so neither release was published. In those runs dependency
compilation finishes after ~26 minutes and the `lancedb` crate compile +
fat-LTO step was still running after 63 minutes.

Move the job to the org's `windows-2025-8x-x64` larger runner and raise
the timeout to 150 minutes. Fat LTO stays, since the thin-LTO wheel
exceeds PyPI's 100 MiB limit.

The final fat-LTO step is largely single-threaded, so the gain from 8
cores is mainly in the parallel dependency phase plus faster/larger
hardware; the PR run of this workflow is the first measurement of fat
LTO on this runner.
2026-09-24 01:04:18 +08:00

228 lines
8.2 KiB
YAML

name: PyPI Publish
on:
push:
tags:
- 'v*'
pull_request:
# This should trigger a dry run (we skip the final publish step)
paths:
- .github/workflows/pypi-publish.yml
- .github/workflows/build_linux_wheel/action.yml
- .github/workflows/build_mac_wheel/action.yml
- .github/workflows/build_windows_wheel/action.yml
- Cargo.toml # Change in dependency frequently breaks builds
- Cargo.lock
env:
PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
permissions:
contents: read
# Without this, a force-push to a PR leaves the previous run going -- including
# a long fat-LTO Windows job and a billed arm64 wheel build.
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
linux:
name: Python ${{ matrix.config.package_name }} ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
timeout-minutes: 60
strategy:
matrix:
config:
- platform: x86_64
manylinux: "2_28"
extra_args: "--features fp16kernels"
runner: ubuntu-22.04
package_name: "lancedb"
rustflags: ""
# For successful fat LTO builds, we need a large runner to avoid OOM errors.
- platform: aarch64
manylinux: "2_28"
extra_args: "--features fp16kernels"
runner: ubuntu-2404-8x-arm64
package_name: "lancedb"
rustflags: ""
# `lancedb-compat`: pre-Haswell-friendly variant for x86_64 hosts
# without AVX2 (Sandy Bridge / Ivy Bridge / Westmere on Intel,
# Bulldozer / Piledriver / Steamroller on AMD). Compiled at the
# `x86-64-v2` baseline; runtime SIMD dispatch in lance-linalg
# picks the appropriate tier (scalar / AVX / AVX+FMA / AVX2+FMA
# / AVX-512) at load time. Same import as `lancedb` -- conflicts
# at install time, so users pick one.
- platform: x86_64
manylinux: "2_28"
extra_args: ""
runner: ubuntu-22.04
package_name: "lancedb-compat"
rustflags: "-Ctarget-cpu=x86-64-v2"
runs-on: ${{ matrix.config.runner }}
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Add swap for Arm fat LTO
if: matrix.config.platform == 'aarch64'
shell: bash
run: |
swap_file="$RUNNER_TEMP/lancedb-swap"
sudo fallocate --length 16G "$swap_file"
sudo chmod 600 "$swap_file"
sudo mkswap "$swap_file"
sudo swapon "$swap_file"
free -h
- uses: ./.github/workflows/build_linux_wheel
with:
python-minor-version: 10
args: "--release --strip ${{ matrix.config.extra_args }}"
arm-build: ${{ matrix.config.platform == 'aarch64' }}
manylinux: ${{ matrix.config.manylinux }}
package-name: ${{ matrix.config.package_name }}
rustflags: ${{ matrix.config.rustflags }}
- uses: actions/upload-artifact@v7
if: startsWith(github.ref, 'refs/tags/v')
with:
name: wheels-linux-${{ matrix.config.package_name }}-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
path: target/wheels/*.whl
if-no-files-found: error
mac:
timeout-minutes: 90
runs-on: ${{ matrix.config.runner }}
strategy:
matrix:
config:
- target: aarch64-apple-darwin
runner: warp-macos-14-arm64-6x
env:
MACOSX_DEPLOYMENT_TARGET: 10.15
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: "3.13"
- uses: ./.github/workflows/build_mac_wheel
with:
python-minor-version: 10
args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
- uses: actions/upload-artifact@v7
if: startsWith(github.ref, 'refs/tags/v')
with:
name: wheels-mac-${{ matrix.config.target }}
path: target/wheels/lancedb-*.whl
if-no-files-found: error
windows:
# The fat-LTO build of the `lancedb` crate does not finish within 90 minutes
# on the 4-core standard runner, so use the 8-core larger runner with extra
# headroom.
timeout-minutes: 150
runs-on: windows-2025-8x-x64
env:
# link.exe is single-threaded and the long pole on Windows builds. Use
# rustc's bundled lld-link instead.
CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: rust-lld
# Keep the repository's fat LTO / 1 codegen unit release profile to leave
# headroom below PyPI's file-size limit for Windows wheels.
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v6
with:
python-version: "3.13"
# NOTE: caching cargo here would be a no-op. This workflow only runs on
# tags and PRs, and GitHub only lets a run restore caches from its own ref
# or the default branch -- so with no run on main there is nothing that
# can populate an entry the release build would be allowed to read. Fixing
# this needs a main/nightly trigger (which would also catch wheel-build
# breakage before a release); the build time here is otherwise dominated
# by the fat-LTO link, which no cache avoids.
- uses: ./.github/workflows/build_windows_wheel
with:
python-minor-version: 10
args: "--release --strip"
- uses: actions/upload-artifact@v7
if: startsWith(github.ref, 'refs/tags/v')
with:
name: wheels-windows
path: target/wheels/lancedb-*.whl
if-no-files-found: error
publish:
name: Publish wheels
if: startsWith(github.ref, 'refs/tags/v')
needs: [linux, mac, windows]
runs-on: ubuntu-latest
permissions:
id-token: write
contents: read
steps:
- uses: actions/checkout@v6
- name: Download wheel artifacts
uses: actions/download-artifact@v8
with:
pattern: wheels-*
path: target/wheels
merge-multiple: true
- name: List wheels
run: ls -la target/wheels
- name: Choose repo
id: choose_repo
run: |
if [[ ${{ github.ref }} == *beta* ]]; then
echo "repo=fury" >> $GITHUB_OUTPUT
else
echo "repo=pypi" >> $GITHUB_OUTPUT
fi
- name: Publish to Fury
if: steps.choose_repo.outputs.repo == 'fury'
env:
FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
run: |
shopt -s nullglob
WHEELS=(target/wheels/*.whl)
if [[ ${#WHEELS[@]} -eq 0 ]]; then
echo "No wheels found in target/wheels/" >&2
exit 1
fi
for WHEEL in "${WHEELS[@]}"; do
echo "Uploading $WHEEL to Fury"
curl -f -F package=@"$WHEEL" "https://$FURY_TOKEN@push.fury.io/lancedb/"
done
# NOTE: pypa/gh-action-pypi-publish must be invoked directly from a
# workflow file, not from inside a composite action. When called from a
# composite, `github.action_repository` is empty (actions/runner#2473)
# and the action falls back to `github.repository`, producing a bogus
# `docker://ghcr.io/<repo>:<ref>` image reference that GHA tries to pull.
- name: Publish to PyPI
if: steps.choose_repo.outputs.repo == 'pypi'
uses: pypa/gh-action-pypi-publish@release/v1
with:
packages-dir: target/wheels/
report-failure:
name: Report Workflow Failure
runs-on: ubuntu-latest
needs: [linux, mac, windows, publish]
permissions:
contents: read
issues: write
if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
steps:
- uses: actions/checkout@v6
- uses: ./.github/actions/create-failure-issue
with:
job-results: ${{ toJSON(needs) }}
workflow-name: ${{ github.workflow }}