onnxruntime/tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-ci-pipeline.yml
jignparm d14e65a224
Finer control over when Python tests are run (#1023)
* Finer control over when Python tests are run

* add --build_wheel to linux pipeline, instead of run_build.sh

* add --build_wheel to all ci configurations

* update per review comments
2019-05-15 18:30:18 -07:00

16 lines
896 B
YAML

jobs:
- job: Linux_CI_GPU_TENSORRT_Dev
pool: Linux-GPU-CUDA10
steps:
- template: templates/set-test-data-variables-step.yml
# There are some tests in 20190130.zip that TensorRT can't run. Instead here use 20181210 opset8 for TensorRT test.
- script: 'tools/ci_build/github/linux/run_dockerbuild.sh -o ubuntu16.04 -d tensorrt -r $(Build.BinariesDirectory) -x "--build_wheel --test_data_url https://onnxruntimetestdata.blob.core.windows.net/models/20181210.zip --test_data_checksum a966def7447f4ff04f5665bca235b3f3"'
displayName: 'Command Line Script'
- task: ms.vss-governance-buildtask.governance-build-task-component-detection.ComponentGovernanceComponentDetection@0
displayName: 'Component Detection'
condition: and(succeeded(), in(variables['Build.Reason'], 'IndividualCI', 'BatchedCI'))
- template: templates/clean-agent-build-directory-step.yml