Conversation
JohannesGaessler
approved these changes
Jan 25, 2026
Contributor
|
The test failure here seems to be due to attention sinks in a configuration that does not appear in actual models. But there also seems to be a more serious issue. |
Member
Author
|
Let me know if you prefer to adjust the tests in some way in this PR, or feel free to push directly here. |
Contributor
|
In terms of correctness the new functionality should be covered with the test case added in #19115 . The kernel selection logic specific for GLM 4.7 Flash should only affect performance. |
f0079c9 to
5e288b8
Compare
Member
Author
@JohannesGaessler How would you like to handle the sinks for this shape? Probably it's fine to add a check in |
5e288b8 to
2f83f9e
Compare
4b1tQu4ntN3k0
pushed a commit
to 4b1tQu4ntN3k0/llama.cpp
that referenced
this pull request
Feb 2, 2026
shaofeiqi
pushed a commit
to qualcomm/llama.cpp
that referenced
this pull request
Feb 6, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Might be a good idea to have a test that exercises GQA=20 in order to catch any potential regressions.