[UT] Fix test_print UTs #2867
Merged
[UT] Fix test_print UTs #2867
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
quintinwang5
requested review from
Dewei-Wang-sh,
chengjunlu,
etiotto and
whitneywhtsang
chengjunlu
reviewed
Nov 29, 2024
| return torch.xpu.current_stream().sycl_queue | ||
|
|
||
| def wait(self): | ||
| self.wait_on_sycl_queue(self.get_sycl_queue()) |
Contributor
There was a problem hiding this comment.
Can we use the torch.xpu.current_stream().wait()?
It is easy for us to decouple the SYCL runtime in triton to torch.
Contributor
Author
There was a problem hiding this comment.
Seems torch does not provide such a wait now.
Contributor
There was a problem hiding this comment.
Let's revisit the runtime code in the future. I think it is ok for now.
chengjunlu
approved these changes
Nov 29, 2024
victor-eds
approved these changes
Dec 2, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
printworks now on DLE 2025.0.0. Buttest_printUTs still fail. There are two reason:printwhile we usesycl::queuefromtorch. So thequeuecannot be synced before the exiting of subprocess.torch.xpu.synchronize()does not work because it just sync onreserved streams. (See the comment). Accroding to my test, our print kernels were not waited on.So I add an
launch_exit_hookto wait on that queue.