onnxruntime/tools/ci_build/github/azure-pipelines/linux-multi-gpu-tensorrt-ci-pipeline.yml
Hector Li 640f71c91b
Enable Gpu multi-device test for CUDA EP and Trt EP
Enable multi-device test for GPU
* Add build pipeline for TensorRT multi-GPU test
* Add code to disable fp16 test if hardware architecture not supported
* Add option to set the device id in onnx_test_runner for model tests
2019-10-14 11:16:34 -07:00

9 lines
No EOL
426 B
YAML

jobs:
- template: templates/linux-ci.yml
parameters:
AgentPool : 'Linux-Multi-GPU'
JobName: 'Linux_CI_Multi_GPU_TensorRT_Dev'
# The latest TensorRT container (R19.09) only supports ubuntu18.04
BuildCommand: 'tools/ci_build/github/linux/run_dockerbuild.sh -o ubuntu18.04 -d tensorrt -r $(Build.BinariesDirectory) -p 3.6 -x "--enable_multi_device_test"'
DoNugetPack: 'false'
ArtifactName: 'drop-linux'