Add optimized bert ops #100
Open
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
MIGraphX has enabled this support as part of the latest release. This allows Onnxruntime MIGraphX EP to parse in Attention and SkipLayernormalization operators and pass them to the MIGraphX API for further processing
TedThemistokleous
force-pushed
the
add_optimized_bert_ops
branch
from
aa3ab61 to
177a206
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Outdated suggestions cannot be applied.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.
Description
Required operators that appear when we use an Onnxruntime Optimized version of BERT Large
Motivation and Context
Required to support the following Microsoft Contrib ops
Attention - ROCm/AMDMIGraphX#3816
SkipLayerNormalization - ROCm/AMDMIGraphX#3865
To be merged once the following MIGraphX PRs are pulled in and used in latest ROCm Release