Add return_attention support to Generator #3488

Workflow file for this run

	name: CI

	on:
	push:
	branches:
	- "**"
	tags:
	- v*
	pull_request:
	branches:
	- master

	jobs:
	build-and-test-cpp-x86_64:
	runs-on: ${{ matrix.os }}
	env:
	CT2_VERBOSE: 1
	strategy:
	matrix:
	os: [ubuntu-22.04]
	backend: [mkl, dnnl]

	steps:
	- uses: actions/checkout@v4
	with:
	submodules: recursive

	- name: Install Intel oneAPI
	if: startsWith(matrix.os, 'ubuntu')
	run: \|
	wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
	sudo apt-key add *.PUB
	sudo sh -c 'echo "deb https://apt.repos.intel.com/oneapi all main" > /etc/apt/sources.list.d/oneAPI.list'
	sudo apt-get update

	- name: Configure with MKL
	if: startsWith(matrix.os, 'ubuntu') && matrix.backend == 'mkl'
	env:
	CT2_USE_MKL: 1
	MKL_VERSION: 2023.0.0
	run: \|
	sudo apt-get install -y intel-oneapi-mkl-devel-$MKL_VERSION
	cmake -DCMAKE_INSTALL_PREFIX=$PWD/install -DBUILD_TESTS=ON .

	- name: Configure with DNNL
	if: startsWith(matrix.os, 'ubuntu') && matrix.backend == 'dnnl'
	env:
	DNNL_VERSION: 2023.0.0-25399
	run: \|
	sudo apt-get install -y intel-oneapi-dnnl-devel=$DNNL_VERSION intel-oneapi-dnnl=$DNNL_VERSION
	cmake -DCMAKE_INSTALL_PREFIX=$PWD/install -DBUILD_TESTS=ON -DWITH_MKL=OFF -DOPENMP_RUNTIME=COMP -DWITH_DNNL=ON .

	- name: Build
	run: \|
	make -j $(nproc) install

	- name: Download test data
	working-directory: tests/data/models
	run: \|
	wget https://opennmt-models.s3.amazonaws.com/pi_lm_step_5000.pt
	wget https://opennmt-models.s3.amazonaws.com/transliteration-aren-all.tar.gz
	tar xf transliteration-aren-all.tar.gz

	- name: Test MKL
	if: matrix.backend == 'mkl'
	env:
	CT2_USE_MKL: 1
	run: \|
	tests/ctranslate2_test tests/data
	- name: Test DNNL
	if: matrix.backend == 'dnnl'
	run: \|
	tests/ctranslate2_test tests/data

	build-and-test-cpp-x86_64-address_sanitizer:
	runs-on: ubuntu-22.04
	env:
	CT2_VERBOSE: 1

	steps:
	- uses: actions/checkout@v4
	with:
	submodules: recursive

	- name: Install Intel oneAPI
	run: \|
	wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
	sudo apt-key add *.PUB
	sudo sh -c 'echo "deb https://apt.repos.intel.com/oneapi all main" > /etc/apt/sources.list.d/oneAPI.list'
	sudo apt update

	- name: Install MKL
	env:
	CT2_USE_MKL: 1
	MKL_VERSION: 2023.0.0
	run: \|
	sudo apt install -y intel-oneapi-mkl-devel-$MKL_VERSION

	- name: Install Clang
	run: \|
	sudo apt install -y clang

	- name: Configure with MKL and Clang
	env:
	CT2_USE_MKL: 1
	run: \|
	cmake -DCMAKE_INSTALL_PREFIX=$PWD/install -DBUILD_TESTS=ON -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++ -DENABLE_ADDRESS_SANITIZER=ON -DCMAKE_BUILD_TYPE=Debug .

	- name: Build
	run: \|
	make -j $(nproc) install

	- name: Download test data
	working-directory: tests/data/models
	run: \|
	wget https://opennmt-models.s3.amazonaws.com/pi_lm_step_5000.pt
	wget https://opennmt-models.s3.amazonaws.com/transliteration-aren-all.tar.gz
	tar xf transliteration-aren-all.tar.gz

	- name: Test AddressSanitizer
	env:
	CT2_USE_MKL: 1
	run: \|
	ASAN_OPTIONS=detect_leaks=1:print_stats=1 tests/ctranslate2_test tests/data

	build-and-test-cpp-arm64:
	runs-on: ${{ matrix.os }}
	env:
	CT2_VERBOSE: 1
	strategy:
	matrix:

	include:
	- os: ubuntu-22.04-arm
	backend: openblas
	- os: macos-15
	backend: ruy
	steps:
	- uses: actions/checkout@v4
	with:
	submodules: recursive

	- name: Build with OpenBLAS and Ruy
	if: matrix.backend == 'openblas'
	run: \|
	wget https://github.com/xianyi/OpenBLAS/archive/v0.3.13.tar.gz
	tar xzvf v0.3.13.tar.gz
	cd OpenBLAS-0.3.13
	make TARGET=ARMV8 NO_LAPACK=1 -j $(nproc)
	sudo make PREFIX=/usr/local install -j $(nproc)
	cd ..
	export OpenBLAS_HOME=/usr/local
	cmake \
	-DOPENMP_RUNTIME=COMP \
	-DCMAKE_INSTALL_PREFIX=$PWD/install \
	-DWITH_MKL=OFF \
	-DWITH_OPENBLAS=ON \
	-DWITH_RUY=ON \
	-DBUILD_TESTS=ON \
	.
	make -j $(nproc) install

	- name: Build Ruy
	if: matrix.backend == 'ruy'
	run: \|
	CMAKE_EXTRA_OPTIONS='-DCMAKE_OSX_ARCHITECTURES=arm64 -DWITH_ACCELERATE=ON -DWITH_MKL=OFF -DOPENMP_RUNTIME=NONE -DWITH_RUY=ON'
	cmake -DCMAKE_POLICY_VERSION_MINIMUM=3.5 \
	-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=ON \
	-DCMAKE_INSTALL_PREFIX=$PWD/install \
	-DBUILD_TESTS=ON \
	$CMAKE_EXTRA_OPTIONS \
	.
	make -j $(nproc) install

	- name: Download test data
	run: \|
	wget https://opennmt-models.s3.amazonaws.com/transliteration-aren-all.tar.gz
	tar xf transliteration-aren-all.tar.gz -C tests/data/models/

	- name: Test
	run: \|
	tests/ctranslate2_test tests/data

	build-python-wheels:
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-22.04, windows-2022]
	arch: [auto64]
	include:
	- os: ubuntu-22.04
	arch: aarch64
	- os: macos-15
	arch: arm64
	- os: macos-15-intel
	arch: x86_64

	steps:
	- uses: actions/checkout@v4
	with:
	submodules: recursive

	- uses: docker/setup-qemu-action@v2
	if: ${{ matrix.arch == 'aarch64' }}
	name: Set up QEMU

	- name: Build wheels
	uses: pypa/cibuildwheel@v3.2.1
	with:
	package-dir: python
	output-dir: python/wheelhouse
	env:
	CIBW_ENVIRONMENT_PASS_LINUX: CIBW_ARCHS
	CIBW_ENVIRONMENT_WINDOWS: CTRANSLATE2_ROOT='${{ github.workspace }}\install'
	CIBW_ENVIRONMENT_MACOS: "CTRANSLATE2_ROOT='/usr/local' MACOSX_DEPLOYMENT_TARGET=11.00"
	CIBW_BEFORE_ALL_LINUX: python/tools/prepare_build_environment_linux.sh
	CIBW_BEFORE_ALL_MACOS: python/tools/prepare_build_environment_macos.sh
	CIBW_BEFORE_ALL_WINDOWS: bash python/tools/prepare_build_environment_windows.sh
	CIBW_BEFORE_BUILD: pip install -r python/install_requirements.txt
	CIBW_MANYLINUX_X86_64_IMAGE: manylinux_2_28
	CIBW_MANYLINUX_AARCH64_IMAGE: manylinux_2_28
	CIBW_ARCHS: ${{ matrix.arch }}
	CIBW_SKIP: "-musllinux_"

	- name: Upload Python wheels
	uses: actions/upload-artifact@v4
	with:
	name: python-wheels-${{ runner.os }}-${{ matrix.arch }}
	path: python/wheelhouse

	build-python-wheels-rocm:
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	os: [ubuntu-24.04, windows-2025]

	steps:
	- uses: actions/checkout@v6
	with:
	submodules: recursive

	- name: Build wheels
	uses: pypa/cibuildwheel@v3.2.1
	with:
	package-dir: python
	output-dir: python/wheelhouse
	env:
	CIBW_ENVIRONMENT_LINUX: ROCM_PATH=/opt/rocm LD_LIBRARY_PATH=/opt/rocm/lib/llvm/lib:$LD_LIBRARY_PATH
	CIBW_ENVIRONMENT_WINDOWS: CTRANSLATE2_ROOT='${{ github.workspace }}\install'
	CIBW_BEFORE_ALL_LINUX: python/tools/prepare_build_environment_linux_rocm.sh
	CIBW_BEFORE_ALL_WINDOWS: bash python/tools/prepare_build_environment_windows_rocm.sh
	CIBW_BEFORE_BUILD: pip install -r python/install_requirements.txt
	CIBW_MANYLINUX_X86_64_IMAGE: manylinux_2_28
	CIBW_ARCHS: auto64
	CIBW_SKIP: "-musllinux_"
	CIBW_REPAIR_WHEEL_COMMAND_LINUX: 'auditwheel repair -w {dest_dir} --exclude "/opt/rocm/lib/lib*" {wheel}'

	- name: Upload Python wheels
	uses: actions/upload-artifact@v6
	with:
	name: rocm-python-wheels-${{ runner.os }}
	path: python/wheelhouse


	# We could test the Python wheels using cibuildwheel but we prefer to run the tests outside
	# the build environment to ensure wheels correctly embed all dependencies.
	test-python-wheels:
	needs: [build-python-wheels]
	runs-on: ${{ matrix.os }}
	strategy:
	matrix:
	include:
	- os: ubuntu-22.04
	artifact_pattern: python-wheels-Linux-auto64
	wheel_pattern: "cp310manylinux*x86_64.whl"

	- os: ubuntu-22.04-arm
	artifact_pattern: python-wheels-Linux-aarch64
	wheel_pattern: "cp310manylinux*_aarch64.whl"

	- os: windows-2022
	artifact_pattern: python-wheels-Windows-auto64
	wheel_pattern: "cp310win*amd64.whl"

	- os: macos-15
	artifact_pattern: python-wheels-macOS-arm64
	wheel_pattern: "cp310macosx*arm64.whl"

	steps:
	- name: Set up Python 3.10.11
	uses: actions/setup-python@v5
	with:
	python-version: "3.10.11"

	- uses: actions/checkout@v4

	- name: Prepare test environment
	shell: bash
	run: \|
	./python/tools/prepare_test_environment.sh

	- name: Download Python wheels
	uses: actions/download-artifact@v4
	with:
	pattern: ${{ matrix.artifact_pattern }}
	merge-multiple: true
	path: .

	- name: Install wheel
	shell: bash
	run: \|
	pip install ${{ matrix.wheel_pattern }}

	- name: Test Python wheel
	run: \|
	pytest -v python/tests/ --ignore=python/tests/test_opennmt_tf.py


	check-python-style:
	runs-on: ubuntu-latest

	steps:
	- uses: actions/checkout@v4

	- name: Set up Python 3.10.11
	uses: actions/setup-python@v5
	with:
	python-version: "3.10.11"

	- name: Install dependencies
	run: \|
	python -m pip install black==22.* flake8==3.8.* isort==5.*

	- name: Check code format with Black
	working-directory: python
	run: \|
	black --check .

	- name: Check imports order with isort
	working-directory: python
	run: \|
	isort --check-only .

	- name: Check code style with Flake8
	working-directory: python
	if: ${{ always() }}
	run: \|
	flake8 .


	publish-python-wheels-on-pypi:
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	needs: [build-and-test-cpp-x86_64, build-and-test-cpp-arm64, build-python-wheels, test-python-wheels, check-python-style]
	runs-on: ubuntu-22.04

	steps:
	- name: Download Python wheels
	uses: actions/download-artifact@v4
	with:
	pattern: python-wheels-*
	merge-multiple: true
	path: .

	- name: Publish Python wheels to PyPI
	uses: pypa/gh-action-pypi-publish@release/v1
	with:
	user: __token__
	password: ${{ secrets.PYPI_API_TOKEN }}
	packages-dir: .


	build-and-push-docker-images:
	runs-on: ubuntu-22.04
	strategy:
	matrix:
	gpu: [cuda, rocm]

	steps:
	- uses: actions/checkout@v4
	with:
	submodules: recursive

	- name: Show disk and docker usage (before cleanup)
	run: \|
	df -h
	echo " -= Docker System =-"
	docker system df \|\| true

	- name: Free disk space (cleanup heavy preinstalled directories + docker prune)
	run: \|
	echo " -= Removing big preinstalled directories (shouldn't remove the needed tools) =-"
	sudo rm -rf /opt/hostedtoolcache \|\| true
	sudo rm -rf /usr/share/dotnet \|\| true
	sudo rm -rf /usr/lib/jvm \|\| true
	sudo rm -rf /usr/local/lib/android \|\| true
	echo " -= Running docker prune =-"
	docker system prune -af --volumes \|\| true
	docker builder prune -af \|\| true

	- name: Show disk and docker usage (after cleanup)
	run: \|
	df -h
	echo " -= Docker System =-"
	docker system df \|\| true

	- name: Build Docker images
	run: \|
	./docker/build_all.sh latest 0 ${{ matrix.gpu }}

	- name: Login to DockerHub
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	uses: docker/login-action@v2
	with:
	registry: ghcr.io
	username: ${{ github.actor }}
	password: ${{ secrets.GITHUB_TOKEN }}

	- name: Push Docker images
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	run: \|
	./docker/build_all.sh ${GITHUB_REF##*/v} 1 ${{ matrix.gpu }}


	build-and-deploy-docs:
	runs-on: ubuntu-latest
	needs: [check-python-style, build-python-wheels, build-python-wheels-rocm]

	permissions:
	contents: write
	steps:
	- uses: actions/checkout@v4
	- name: Set up Python 3.10.11
	uses: actions/setup-python@v5
	with:
	python-version: "3.10.11"
	- name: Download CTranslate2 wheels
	uses: actions/download-artifact@v4
	with:
	pattern: python-wheels-${{ runner.os }}-*
	merge-multiple: true
	path: .
	- name: Install CTranslate2 wheel
	run: \|
	pip install cp310manylinux*x86_64.whl
	- name: Install dependencies to build docs
	working-directory: docs
	run: \|
	python -m pip install -r requirements.txt
	- name: Build docs
	working-directory: docs
	run: \|
	python generate.py python
	sphinx-build . build
	- name: Deploy docs
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	uses: JamesIves/github-pages-deploy-action@v4
	with:
	folder: docs/build
	clean: true
	- name: Download ROCm wheels and zip for release
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	env:
	GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	run: \|
	mkdir -p release-zips

	gh run download ${{ github.run_id }} \
	--name rocm-python-wheels-Linux \
	--dir temp-linux
	zip -r release-zips/rocm-python-wheels-Linux.zip temp-linux/*
	rm -rf temp-linux

	gh run download ${{ github.run_id }} \
	--name rocm-python-wheels-Windows \
	--dir temp-windows
	zip -r release-zips/rocm-python-wheels-Windows.zip temp-windows/*
	rm -rf temp-windows

	- name: Create GitHub Release
	if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
	uses: softprops/action-gh-release@v2
	with:
	files: release-zips/*.zip

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add return_attention support to Generator #3488

Workflow file

Add return_attention support to Generator #3488

Uh oh!

Workflow file for this run