Fix ERNIE GPU inference with shared params in multihead matmul #27121
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
|
Thanks for your contribution! |
cryoco
changed the title
cryoco
added a commit
to cryoco/Paddle
that referenced
this pull request
Sep 8, 2020
cryoco
added a commit
to cryoco/Paddle
that referenced
this pull request
Sep 15, 2020
cryoco
added a commit
that referenced
this pull request
Sep 16, 2020
* fix multihead matmul shared params (#27121) * fix multihead matmul shared params
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Outdated suggestions cannot be applied.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.
PR types
Bug fixes
PR changes
Others
Describe
If weights or biases in qkv's fc are shared by multiple multihead_matmul patterns, we do not support this kind of fusion, multihead_matmul_fuse_pass_v2 will not take effect.