[Revert]Revert unquantized linear nz support #2893
Closed
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
|
Note Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported. |
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
This reverts commit 7b2ecc1. Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
anon189Ty
force-pushed
the
unquantized_linear_nz_support
branch
from
c2ce6db to
b3db04e
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2893 +/- ##
==========================================
+ Coverage 74.76% 74.89% +0.12%
==========================================
Files 150 154 +4
Lines 20891 21241 +350
==========================================
+ Hits 15620 15908 +288
- Misses 5271 5333 +62
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
|
756b8a1 merged by this already. |
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Outdated suggestions cannot be applied.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.
What this PR does / why we need it?
If we want a performance improvement by cast the format of weights from ND to NZ in unquantized linear, we need to transpose the weight shape too. But will case some errors in current code when running some models such as DeepSeek-V3-w4a8. Currently temporarily roll back.
Does this PR introduce any user-facing change?
How was this patch tested?