ggml-cpu: arm64: Fix wrong memcpy length for q4_K block_interleave == 4#19575
Merged
taronaeo merged 1 commit intoggml-org:masterfrom Feb 13, 2026
Merged
ggml-cpu: arm64: Fix wrong memcpy length for q4_K block_interleave == 4#19575taronaeo merged 1 commit intoggml-org:masterfrom
taronaeo merged 1 commit intoggml-org:masterfrom
Conversation
Collaborator
|
Yep I can confirm that this fixes the stack smashing problem. Thank you very much! |
Collaborator
|
Merge on green? Your call :) |
taronaeo
approved these changes
Feb 13, 2026
Collaborator
Author
|
Yeah, I can merge, but if you see it before I do, feel free to press the button :) |
ronaldmannak
pushed a commit
to PicoMLX/llama.cpp
that referenced
this pull request
Feb 16, 2026
(cherry picked from commit cc2aa81)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
#19561 reports issues with the stack for Q4_K.
I can't reproduce the issue locally, but the
make_block_q4_Kx8function would write past the buffer size 4 extra bytes, which could be the issue.@taronaeo, since you found the problem, are you able to check if this patch fixes it?
Q6_K and Q5_K (#19356, still opened at the moment this description was written) already address this problem.