Add new test cases for the all_gather CCL op #2372
Open
Conversation
This file contains 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
- Test with various all_gather_dim attributes. - Test with various input tensor ranks. - Test with fp32 and bf16.
- Test with increased dimension on gathered/non-gathered axis
hkwonTT
force-pushed
the
more_all_gather_testcases
branch
from
6ceca08 to
e3e33ce
Compare
hkwonTT
requested review from
nsmithtt,
tapspatel,
mtopalovicTT,
ajakovljevicTT,
mrakitaTT,
vladimirjovanovicTT,
wooseokTT and
sdjukicTT
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Outdated suggestions cannot be applied.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.
Ticket
#2368
Problem description
We have only basic silicon tests with all_gather operation.
What's changed
Add new test cases for the all_gather CCL op
Tests with tensors that are not multiples of the tile size were not included. They cannot be run with the runtime due to this issue: tenstorrent/tt-metal#16870. These testcases will be updated when the runtime issue resolved.
All tests executed successfully, and their outputs matched the golden results from torch distributed.
Checklist