mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-30 20:18:08 +00:00
5a7f65b831
1. Fix training e2e pipeline. The failure was caused by my recent change #7632. The fix is adding "--cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=70" to the build parameters because the machines are with V100 GPUs. 2. Simplify Nuphar pipeline. It doesn't need to install a separated ONNX version(1.5.0) 3. Fix a problem that run_dockerbuild.sh ignored OS version parameter. Now because it starts to take effect, I also set python version to the system default one(3.8 for ubuntu 20.04)
64 lines
2.7 KiB
YAML
64 lines
2.7 KiB
YAML
trigger: none
|
|
|
|
jobs:
|
|
- job: Onnxruntime_Linux_GPU_ORTModule_Test
|
|
|
|
timeoutInMinutes: 120
|
|
pool: 'Linux-Single-GPU-V100'
|
|
|
|
steps:
|
|
- checkout: self
|
|
clean: true
|
|
submodules: recursive
|
|
|
|
- template: templates/run-docker-build-steps.yml
|
|
parameters:
|
|
RunDockerBuildArgs: |
|
|
-o ubuntu20.04 -p 3.8 -p 3.8 -d gpu -r $(Build.BinariesDirectory) \
|
|
-t onnxruntime_ortmodule_tests_image \
|
|
-x " \
|
|
--config RelWithDebInfo \
|
|
--enable_training \
|
|
--update --build \
|
|
--build_wheel --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=70 \
|
|
" \
|
|
-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()
|
|
|
|
- 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/bert-data" -d "/bert_data"
|
|
displayName: 'Mount bert-data'
|
|
condition: succeededOrFailed()
|
|
|
|
- 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/hf-models-cache" -d "/hf_models_cache"
|
|
displayName: 'Mount hf-models-cache'
|
|
condition: succeededOrFailed()
|
|
|
|
# Entry point for all ORTModule tests
|
|
# The onnxruntime folder is deleted in the build directory
|
|
# to enforce use of the onnxruntime wheel
|
|
- script: |
|
|
docker run \
|
|
--gpus all \
|
|
--shm-size=1024m \
|
|
--rm \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume /mnist:/mnist \
|
|
--volume /bert_data:/bert_data \
|
|
--volume /hf_models_cache:/hf_models_cache \
|
|
onnxruntime_ortmodule_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_tests.py --mnist /mnist --bert_data /bert_data/hf_data/glue_data/CoLA/original/raw --transformers_cache /hf_models_cache/huggingface/transformers' --cwd /build/RelWithDebInfo" \
|
|
displayName: 'Run orttraining_ortmodule_tests.py'
|
|
condition: succeededOrFailed()
|
|
timeoutInMinutes: 60
|
|
|
|
- template: templates/component-governance-component-detection-steps.yml
|
|
parameters:
|
|
condition: 'succeeded'
|
|
|
|
- template: templates/clean-agent-build-directory-step.yml
|