fix test_attention #17883
Closed
fix test_attention #17883
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
Member
|
cc: @MasterJH5574 |
Member
|
@cyx-6 can you also help to cross check this |
Member
|
sorry for the delayed note, i take a closer look. In principle we should not pass Expr as part of Attrs and always treat Attrs as constant, as a result, we cannot take this change as it is. We can however, require the attention funciton to optionally takes a bias argument, and the printer should be updated to be able to print out the bias or remove bias as needed. So the correct fix here would be to fix the printer and deduction function of attention op, if we allow optional bias in the attention operator |
xinxilwl
force-pushed
the
inconsistent-attention-bias
branch
from
1ad5dda to
a65d3d4
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
I fixed the bug below:
17587 fails on tvm.ir.assert_structural_equal in tests/python/relax/test_transform_legalize_ops_nn.py