Conversation
alessiodevoto
approved these changes
Apr 8, 2026
Collaborator
|
/ok to test ac07ed2 |
Replace quantile-based threshold with topk ranking in compute_important_per_layer to match the pattern used by all other presses and avoid overshooting the target compression ratio due to quantile interpolation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Signed-off-by: SimJeg <sjegou@nvidia.com>
Collaborator
Author
|
/ok to test efc294b |
Collaborator
Author
|
/ok to test 31b4a0e |
Collaborator
Author
|
/ok to test 8b5325b |
Collaborator
Author
|
/ok to test 3fd743a |
CompactorPress, LeverageScorePress, and NonCausalAttnPress OOM when run with Qwen3-4B on the L4 GPU (23GB), corrupting CUDA state and cascading into 31 test failures. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Collaborator
Author
|
/ok to test 2982401 |
This reverts commit 2982401.
Signed-off-by: SimJeg <sjegou@nvidia.com>
Collaborator
Author
|
/ok to test c27fe1c |
Signed-off-by: SimJeg <sjegou@nvidia.com>
Collaborator
Author
|
/ok to test f04313c |
alessiodevoto
approved these changes
Apr 9, 2026
Collaborator
alessiodevoto
left a comment
alessiodevoto
left a comment
There was a problem hiding this comment.
LGTM! This one should fix #209
Follow-ups:
- compatibility with
transformers > 5.2 - Consider adding tests without FA
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
KVComposePresscompression ratio failed test because of using quantile