[cogview4][feat] Support attention mechanism with variable-length support and batch packing #11349
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
…nd batch packing Add support for variable-length attention between text and vision tokens while maintaining the original attention pattern. Implement batch packing capability to improve computational efficiency during inference and training.
yiyixuxu
reviewed
Apr 17, 2025
|
let me know what you think too @a-r-r-o-w |
a-r-r-o-w
reviewed
Apr 18, 2025
|
@a-r-r-o-w It has been renamed to |
a-r-r-o-w
reviewed
Apr 18, 2025
|
I have changed back to using |
a-r-r-o-w
approved these changes
Apr 19, 2025
|
@bot /style |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
yiyixuxu
reviewed
Apr 21, 2025
|
@bot /style |
|
Style fixes have been applied. View the workflow run here. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR is primarily aimed at adding native multi-resolution + packing training support to CogView4 to better meet user needs. We have conducted relevant tests in this PR.
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@a-r-r-o-w
@zRzRzRzRzRzRzR