comaniac commented on pull request #6395: URL: https://github.com/apache/incubator-tvm/pull/6395#issuecomment-696874511
> Thanks Cody, I measured the time on a AWS g4dn.4xlarge instance. > > Full with runtime: 6m2.021s > Codegen only: 1m0.358s > Codegen only, removed all integration test models except resnet18_v1 and mobilenet_v2: 0m51.536s > > Seems like the extra models in the integration tests do not consume much time. Thanks for the numbers. Ideally, we should include TensorRT in the CI, so 6 mins should be the number we are referring. @zhiics @tqchen please share your opinions about the testing time. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
