[ONNX] Extend converter for Attention from Microsoft onnxruntime contrib opset #13797
Conversation
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
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment. Generated by tvm-bot |
Contributor
Author
|
@tvm-bot rerun |
KJlaccHoeUM9l
force-pushed
the
agladyshev/dev/attention
branch
from
4a8b581 to
8e7462f
Compare
vvchernov
approved these changes
Jan 19, 2023
Contributor
vvchernov
left a comment
vvchernov
left a comment
There was a problem hiding this comment.
LGTM. I belive that somewhere problems with magic number -10000 from ONNX Runtime will be resolved
Contributor
Author
|
Hello @AndrewZhaoLuo! |
AndrewZhaoLuo
approved these changes
Jan 19, 2023
fzi-peccia
pushed a commit
to fzi-peccia/tvm
that referenced
this pull request
Mar 27, 2023
…rib opset (apache#13797) * add type & shape checking * add base class for Attention converter * add support for 'past' input * add support for 'unidirectional' attribute * fix for 'huggingface implementation' * add common method for calculating Attention * expand test coverage for Attention
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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Outdated suggestions cannot be applied.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.
Earlier I added converter for
QAttention(see PR#13654).In this PR, I've added support for
pastinput andunidirectionalattribute inAttention. I've also moved the common code forQAttentionandAttentioninto a base class.