zhiics edited a comment on issue #7041: URL: https://github.com/apache/tvm/issues/7041#issuecomment-739314684
I see. I think the problem is caused by cuda sort. It is flaky. That's why we wanted to use thrust. Let's skip cuda for this test for now. I thought removing the annotation would skip it, but it is still actually in the enabled list on the GPU CI. ---------------------------------------------------------------- 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: [email protected]
