Fix max token slicing in compression data transform function #672
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
|
In draft for now not to interfere with the current compression experiments cc @KodiaqQ |
andreyanufr
approved these changes
Jul 24, 2024
nikita-savelyevv
added a commit
to nikita-savelyevv/openvino.genai
that referenced
this pull request
Jul 25, 2024
nikita-savelyevv
added a commit
to nikita-savelyevv/openvino.genai
that referenced
this pull request
Aug 19, 2024
nikita-savelyevv
added a commit
to nikita-savelyevv/openvino.genai
that referenced
this pull request
Aug 20, 2024
|
Not needed after #689 was merged |
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Outdated suggestions cannot be applied.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.
Changes
Fix how max token slicing is applied inside data-aware compression
transform_fn.Reason for change
input_idsandattention_maskhave the shape of(B, N), but max token slicing is applied at first instead of the second dimension.