Optimize again for Ernie GPU Inference #22424
Closed
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
Contributor
NHZlX
commented
Feb 3, 2020
•
NHZlX
commented
- optim the multihead fuse pass( fuse the three fc to multihead) and also update the multihead op.
- Add embedding eltwise layernorm pass and embedding eltwise layernorm op.
NHZlX
force-pushed
the
ernie_second_optim
branch
from
baa141a
to
aaca57f
Compare
NHZlX
force-pushed
the
ernie_second_optim
branch
from
aaca57f
to
4080a16
Compare
2. add fused embedding eltwise layernorm pass 3. add fused embedding eltwise layernorm op 4. add embedding eltwise layernorm pass ut test=develop
NHZlX
force-pushed
the
ernie_second_optim
branch
from
4080a16
to
eb79651
Compare
1. delete PADDLE_ENFORCE 2. add more info for PADDLE_ENFORCE_EQ test=develop
optim inplaceReluAdd kernel. test=develop
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Outdated suggestions cannot be applied.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.