onnxruntime/tools/ci_build/github/azure-pipelines/linux-cpu-eager-pipeline.yml
Changming Sun c8524d2dab
Refactor web-ci pipeline and delete eager mode CI pipeline (#15416)
### Description
1. Move it to a separated pool that use the same image as [the public
hosted
pool](https://learn.microsoft.com/en-us/azure/devops/pipelines/agents/hosted?view=azure-devops&tabs=yaml).
Also, create a beta pool which contains the next version image of the
hosted pool, and add jobs in our post merge pipeline to test if the next
version image will break our CI. So, usually we will have at least one
week to prepare.

2. Change the cmake generator in use in our pipelines from "Ninja" to
"MingW Makefile", because the latest version of cmake doesn't work with
the latest version of Ninja. People who prefer Ninja could still use
ninja in their local build by passing "--cmake_generator ninja" to
[build.py](https://github.com/microsoft/onnxruntime/blob/main/tools/ci_build/build.py).

3. Delete eager mode CI pipeline. 


### Motivation and Context
I need to update the software we have in our CI build machines, and I
need to resolve this incompatibility issue. In more detail, the build
error I hit was:

em++: error:
CMakeFilesonnxruntime_mlas_test.dirC_a_work1sonnxruntimetestmlasunittesttest_activation.cpp.o:
No such file or directory
("CMakeFilesonnxruntime_mlas_test.dirC_a_work1sonnxruntimetestmlasunittesttest_activation.cpp.o"
was expected to be an input file, based on the commandline arguments
provided)

After this PR we will deprecate python 3.7 support. The eager mode CI
pipeline is the last one that still use python 3.7. Then we can rework
the PR #10953 made by [fs-eire](https://github.com/fs-eire) last year.

Fixed
[AB#14435](https://aiinfra.visualstudio.com/6a833879-cd9b-44a4-a9de-adc2d818f13c/_workitems/edit/14435)
2023-04-10 10:41:04 -07:00

76 lines
2.7 KiB
YAML

resources:
repositories:
- repository: manylinux
type: Github
endpoint: Microsoft
name: pypa/manylinux
ref: aead4d751c2101e23336aa73f2380df83e7a13f3
jobs:
# This pipeline builds the latest PyTorch commit from source
# and use it in ORT tests. See Dockerfile.manylinux2014_lort_cpu
# for the installation steps. Idally, we should only use one pipeline
# for eager mode and LazyTensor, but we split them due to recent
# PyTorch's breaking changes.
#
# TODO: once ORT eager mode can run with latest PyTorch commit, we
# should
# 1. Set --build_eager_mode when running build.py in the
# first "task" below.
# 2. Copy the second "task" above as the third task below.
- job: BuildAndTestLazyTensor
timeoutInMinutes: 120
workspace:
clean: all
pool: onnxruntime-Linux-CPU-2019
steps:
- checkout: self
clean: true
submodules: recursive
- template: templates/get-docker-image-steps.yml
parameters:
Dockerfile: tools/ci_build/github/linux/docker/Dockerfile.manylinux2014_lort_cpu
Context: tools/ci_build/github/linux/docker
DockerBuildArgs: "--build-arg BUILD_UID=$( id -u )"
Repository: onnxruntimecpubuildlort
- task: CmdLine@2
displayName: 'Build ORT for Python 3.9'
inputs:
script: |
docker run --rm \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory):/build \
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
-e NIGHTLY_BUILD \
-e BUILD_BUILDNUMBER \
onnxruntimecpubuildlort \
/opt/python/cp39-cp39/bin/python3.9 /onnxruntime_src/tools/ci_build/build.py \
--build_dir /build --cmake_generator Ninja \
--config Release \
--skip_submodule_sync \
--build_shared_lib \
--parallel \
--enable_lazy_tensor --enable_training --build_wheel --skip_test \
workingDirectory: $(Build.SourcesDirectory)
- task: CmdLine@2
displayName: 'Test DORT with Python 3.9'
inputs:
script: |
docker run --rm \
--volume $(Build.SourcesDirectory):/onnxruntime_src \
--volume $(Build.BinariesDirectory):/build \
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
-e NIGHTLY_BUILD \
-e BUILD_BUILDNUMBER \
onnxruntimecpubuildlort \
bash -c "
export PYTHONPATH=/build/Release && \
/opt/python/cp39-cp39/bin/python3.9 -m pip install /build/Release/dist/*.whl && \
/opt/python/cp39-cp39/bin/python3.9 /onnxruntime_src/orttraining/orttraining/test/python/orttraining_test_dort.py"
workingDirectory: $(Build.SourcesDirectory)
condition: succeededOrFailed()
- template: templates/clean-agent-build-directory-step.yml