Modify embedlayernorm fusion due to shape node merging#4967
Merged
Conversation
Contributor
|
Please add a test case. |
tianleiwu
reviewed
Sep 1, 2020
tianleiwu
reviewed
Sep 1, 2020
tianleiwu
reviewed
Sep 3, 2020
onnxruntime/test/testdata/transform/fusion/embed_layer_norm_gen.py
Outdated
Show resolved
Hide resolved
wangyems
force-pushed
the
wangye/embedfix
branch
from
f6ad801 to
621566b
Compare
tianleiwu
approved these changes
Sep 8, 2020
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix embedlayernorm fusion for Bert and DistilBert due to "shape" integration
The initial structure(after L1 optimization) may contain multiple shape node after an unique input.
The current implementation makes sure that there is only one "shape" node which have multiple output