mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-20 19:12:24 +00:00
b854f2399d
1. Update manylinux build scripts. This will add [PEP600](https://www.python.org/dev/peps/pep-0600/)(manylinux2 tags) support. numpy has adopted this new feature, we should do the same. The old build script files were copied from https://github.com/pypa/manylinux, but they has been deleted and replaced in the upstream repo. The manylinux repo doesn't have a manylinux2014 branch anymore. So I'm removing the obsolete code, sync the files with the latest master. 2. Update GPU CUDA version from 11.0 to 11.1(after a discussion with PMs). 3. Delete tools/ci_build/github/linux/docker/Dockerfile.manylinux2014_cuda10_2. (Merged the content to tools/ci_build/github/linux/docker/Dockerfile.manylinux2014_cuda11) 4. Modernize the cmake code of how to locate python devel files. It was suggested in https://github.com/onnx/onnx/pull/1631 . 5. Remove `onnxruntime_MSVC_STATIC_RUNTIME` and `onnxruntime_GCC_STATIC_CPP_RUNTIME` build options. Now cmake has builtin support for it. Starting from cmake 3.15, we can use `CMAKE_MSVC_RUNTIME_LIBRARY` cmake variable to choose which MSVC runtime library we want to use. 6. Update Ubuntu docker images that used in our CI build from Ubuntu 18.04 to Ubuntu 20.04. 7. Update GCC version in CUDA 11.1 pipelines from 8.x to 9.3.1 8. Split Linux GPU CI pipeline to two jobs: build the code on a CPU machine then run the tests on another GPU machines. In the past we didn't test our python packages. We only tested the pre-packed files. So we didn't catch the rpath issue in CI build. 9. Add a CentOS machine pool and test our Linux GPU build on real CentOS machines. 10. Rework ARM64 Linux GPU python packaging pipeline. Previously it uses cross-compiling therefore we must static link to C Runtime. But now have pluggable EP API and it doesn't support static link. So I changed to use qemu emulation instead. Now the build is 10x slower than before. But it is more extensible.
54 lines
2 KiB
YAML
54 lines
2 KiB
YAML
trigger: none
|
|
|
|
jobs:
|
|
- job: Onnxruntime_Linux_GPU_ORTModule_Distributed_Test
|
|
|
|
timeoutInMinutes: 120
|
|
pool: 'Linux-Multi-GPU-V100'
|
|
|
|
steps:
|
|
- checkout: self
|
|
clean: true
|
|
submodules: recursive
|
|
|
|
- template: templates/run-docker-build-steps.yml
|
|
parameters:
|
|
RunDockerBuildArgs: |
|
|
-o ubuntu20.04 -d gpu -r $(Build.BinariesDirectory) \
|
|
-t onnxruntime_ortmodule_distributed_tests_image \
|
|
-x " \
|
|
--config RelWithDebInfo \
|
|
--enable_training \
|
|
--update --build \
|
|
--build_wheel \
|
|
" \
|
|
-m \
|
|
-u \
|
|
-e
|
|
DisplayName: 'Build'
|
|
|
|
- bash: tools/ci_build/github/linux/docker/scripts/training/azure_scale_set_vm_mount_test_data.sh -p $(orttrainingtestdata-storage-key) -s "//orttrainingtestdata.file.core.windows.net/mnist" -d "/mnist"
|
|
displayName: 'Mount MNIST'
|
|
condition: succeededOrFailed()
|
|
|
|
# Entry point for all ORTModule distributed tests
|
|
# Refer to orttraining/orttraining/test/python/how_to_add_ortmodule_distributed_ci_pipeline_tests.md for guidelines on how to add new tests to this pipeline.
|
|
- script: |
|
|
docker run \
|
|
--gpus all \
|
|
--shm-size=1024m \
|
|
--rm \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume /mnist:/mnist \
|
|
onnxruntime_ortmodule_distributed_tests_image \
|
|
bash -c "python3 -m pip install /build/RelWithDebInfo/dist/onnxruntime*.whl ; rm -rf /build/RelWithDebInfo/onnxruntime/ ; /build/RelWithDebInfo/launch_test.py --cmd_line_with_args 'python orttraining_ortmodule_distributed_tests.py --mnist /mnist' --cwd /build/RelWithDebInfo" \
|
|
displayName: 'Run orttraining_ortmodule_distributed_tests.py'
|
|
condition: succeededOrFailed()
|
|
timeoutInMinutes: 30
|
|
|
|
- template: templates/component-governance-component-detection-steps.yml
|
|
parameters:
|
|
condition: 'succeeded'
|
|
|
|
- template: templates/clean-agent-build-directory-step.yml
|