onnxruntime/tools/ci_build/github
yf711 0ad0d6ebbf
Unblock Linux MultiGPU TensorRT CI (#16446)
### Description
Revert docker base image to
nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04@sha256:b754c43fe9d62e88862d168c4ab9282618a376dbc54871467870366cacfa456e



### Motivation and Context
The default img env of nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04 has
minor upgrade, which make Linux MultiGPU TensorRT CI (NV12 instance with
Maxwell GPU) fail on three CApiTestGlobalThreadPoolsWithProvider
tests (these three tests have higher error which are above the tolerance)

That minor upgrade includes cudnn 8.7.0->8.9.0, which might be a factor
that make maxwell GPU generator higher error. CIs with T4 GPU are not
affected.
2023-06-21 17:15:39 -07:00
..
android [NNAPI doc] add reducemean to supported op list (#16414) 2023-06-21 00:29:20 -07:00
apple Treat Objective-C static analysis warnings as errors (#16293) 2023-06-09 08:51:49 -07:00
azure-pipelines Set onnxruntime-c local pod path environment variable for react native e2e tests on ci (#16431) 2023-06-21 00:27:36 -07:00
js [js] add API that allows to get package version (#16207) 2023-06-09 16:18:53 -07:00
linux Unblock Linux MultiGPU TensorRT CI (#16446) 2023-06-21 17:15:39 -07:00
pai [ROCm] Delete unused file to fix Component Governance Alert (#16407) 2023-06-19 11:28:32 -07:00
windows Update win-ci-pipeline.yml: enable xnnpack tests (#16244) 2023-06-14 19:12:42 -07:00
Doxyfile_csharp.cfg Implement Optional Metadata support and C# test support (#15314) 2023-04-11 09:41:59 -07:00