GPU implementation for layer normalization operator #8006
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
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
5 times, most recently
from
96b7645
to
601ca1e
Compare
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
from
601ca1e
to
76e188e
Compare
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
from
de369d7
to
243654e
Compare
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
5 times, most recently
from
a41a6bb
to
d5fcfd1
Compare
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
from
d5fcfd1
to
5092f52
Compare
chengduoZH
force-pushed
the
feature/layer_norm_enhancement
branch
2 times, most recently
from
113ea53
to
6773129
Compare
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Outdated suggestions cannot be applied.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.
fix #7987
ElementwiseComputeEx's interface, making it more flexible.Add unit test for scale and biasThere's too much content in this PR, and adding the unit test for scale and bias will be implemented in the next PR.