Fix: Re-enable Sparse Compression for 2of4 Examples#1153
Merged
Conversation
|
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed. |
rahul-tuli
requested review from
brian-dellabetta,
dsikka,
horheynm and
kylesayrs
kylesayrs
previously approved these changes
Feb 14, 2025
Collaborator
kylesayrs
left a comment
kylesayrs
left a comment
There was a problem hiding this comment.
Consider adding a comment about prev vllm versions
horheynm
previously approved these changes
Feb 14, 2025
dsikka
requested changes
Feb 14, 2025
Collaborator
dsikka
left a comment
dsikka
left a comment
There was a problem hiding this comment.
Can we update the E2E test case as well?
dsikka
reviewed
Feb 14, 2025
Collaborator
dsikka
left a comment
dsikka
left a comment
There was a problem hiding this comment.
Should we consider adding a comment to the example about disable_sparse_compression (just that it exists/can be used)?
Collaborator
Author
|
It is there in the readme as a separate section, if anyone wants to try |
rahul-tuli
dismissed stale reviews from horheynm, brian-dellabetta, and kylesayrs
via
d7756df
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
rahul-tuli
force-pushed
the
update-2of4-example
branch
from
d7756df to
8862d8b
Compare
Collaborator
Author
Done and tested! |
brian-dellabetta
approved these changes
Feb 14, 2025
dsikka
approved these changes
Feb 14, 2025
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
6 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.
This PR restores sparse compression for our
2of4examples, which was previously disabled due to a bug in the vLLM Cutlass integration.Background
A bug in the Cutlass integration caused certain sparse-only compressed models to produce gibberish results. To mitigate this issue, we temporarily turned off sparse compression for our
2of4examples.The bug has since been fixed by @tlrmchlsmth in vllm-project/vllm#13198. With this fix in place, we can safely re-enable sparse compression for these examples.
Changes
2of4examples.Testing