[Unity][CUTLASS] Require the residual input to have the same shape as input#14657
Merged
vinx13 merged 1 commit intoapache:unityfrom Apr 19, 2023
Merged
[Unity][CUTLASS] Require the residual input to have the same shape as input#14657vinx13 merged 1 commit intoapache:unityfrom
vinx13 merged 1 commit intoapache:unityfrom
Conversation
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
vinx13
approved these changes
Apr 19, 2023
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In SD UNet, I met a pattern
conv2d -> bias_add -> residual_addwhere the input shape is(2, 16, 16, 1280)and the residual input shape is(2, 1, 1, 1280). Such general broadcast add for the residual block is not supported by cutlass.This was the cause of
nanoutput when using the cutlass BYOC with an improved AMP pass (that allows bias add to be done in fp16, PR later).@vinx13 @yelite @spectrometerHBH