ORT 1.24.6 Cherry Picks#28246
Merged
adrastogi merged 1 commit intorel-1.24.6from Apr 29, 2026
Merged
Conversation
### Description <!-- Describe your changes. --> When copying tensors of sub-byte types (e.g., int4, uint4), two code paths in the CPU EP's CopyCpuTensor function use the element count as the byte count during memcpy, but those types are only 4 bits (0.5 bytes). This causes ORT to copy the incorrect number of bytes, which can cause overflow / corruption. The fix is to replace the math with `Tensor::SizeInBytes()`, which already correctly handles sub-byte packing. There is a second site in `IdentityOp::Compute` which has been refactored to call `CopyCpuTensor` directly, eliminating the duplicated logic. The change also adds regression tests for different variations of this scenario (I was able to use them to reproduce the original issue without the proposed updates). ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> This fixes a problem in the CPU EP in the scenario described above.
sanaa-hamel-microsoft
approved these changes
Apr 28, 2026
tianleiwu
approved these changes
Apr 28, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 cherry-picks the following commits for the release:
#28171 Fix overflow in CopyCpuTensor for sub-byte types