[GPU] Fix: Prevent out-of-bounds read in dequantize merge #32302
+5
−1
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
Lyamin-Roman
reviewed
Oct 6, 2025
src/plugins/intel_gpu/src/graph/graph_optimizer/prepare_quantization.cpp
Outdated
Show resolved
Hide resolved
Lyamin-Roman
approved these changes
Oct 7, 2025
|
build_jenkins |
p-durandin
approved these changes
Oct 7, 2025
Lyamin-Roman
reviewed
Oct 7, 2025
Lyamin-Roman
changed the title
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Outdated suggestions cannot be applied.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.
This PR fixes a segmentation fault in the dequantize merge optimization pass.
The issue was caused by an out-of-bounds memory read when comparing two memory buffers of different sizes. This change adds a guard condition to check that the buffer sizes are equal before attempting to compare their contents.
Fixes #32295