[BugFix][Relay] Fix type relation for batch_matmul #8376
Merged
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
mbrookhart
reviewed
Jun 30, 2021
Comment on lines
382
to
383
| # TODO(mbrookhart): enable once VM supports heterogenous execution | ||
| # @tvm.testing.uses_gpu |
There was a problem hiding this comment.
I thought I'd removed all of these TODO's. Oops! This should work on GPU now, I think
There was a problem hiding this comment.
This is a flaky test that times out sometimes, rebase?
There was a problem hiding this comment.
Everything is fine now, thanks.
mbrookhart
approved these changes
Jun 30, 2021
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Sep 29, 2021
* fix type relation for batch_matmul * fix lint
zxy844288792
pushed a commit
to zxy844288792/tvm
that referenced
this pull request
Mar 4, 2022
* fix type relation for batch_matmul * fix lint
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Outdated suggestions cannot be applied.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.
I find the current implementation of
relay.nn.batch_matmulwill fail given input tensors with shape(Any(), M, K)and(Any(), N, K). This is caused by the wrong implementation ofbatch_matmul's type relation. When the input tensor has a dynamic shape but not all dimensions are dynamic, this relation function will usex's shape directly and output wrong results.For example, given
xwith shape(Any(), 16, 32)andywith shape(Any(), 16, 32), the output shape of current implementation is(Any(), 16, 32).