ORT 1.24.5 Cherry Picks#28100
Merged
adrastogi merged 4 commits intorel-1.24.5from Apr 17, 2026
Merged
Conversation
### Description This change adds a feature to the Compile API, allowing an in-memory OrtModel created via the Model Editor API to be compiled directly without first serializing to a file or buffer. ### 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. --> The Model Editor API and Compile API are both public C APIs in the ONNX Runtime, but until now there was no way to pass a programmatically constructed model directly to compilation. This change attempts to closes that gap (see #26750) and ensures the new code path behaves identically to the established file and buffer paths. --------- Co-authored-by: Aditya Rastogi <adityar@ntdev.microsoft.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
<!-- Describe your changes. --> This change tries to address a problem in the DML EP where AlignToPow2 rounded up tensorByteSize to a 4-byte boundary before the data was read from the source buffer. This caused CreateCpuResource, CreateResource, WriteToFile, and the inputRawData vector construction to read 1–3 bytes past the end of the original tensor data. CreateResource and CreateCpuResource already independently align the D3D12 resource descriptor size, so they work correctly with the original (unaligned) byte count. The fix is to move the alignment to the location where it's needed. <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> This is required because it addresses a crash / incorrect behavior in the DML EP.
### Description <!-- Describe your changes. --> DmlOperatorQuantization21 was missing the tensor reshaping logic that the older DmlOperatorElementwiseQLinear already had. Scalar scale tensors get padded to 4D, but a 5D input stays 5D. DML rejects the dimension mismatch with E_INVALIDARG, and the resulting exception unwind triggers a sized-delete bug in WRL's MakeAllocator which address sanitizer detects. The fix is to port the same logic from the DmlOperatorElementwiseQLinear into this path, so that the dimensions match. ### 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 is required to ensure the DML EP correctly handles this scenario. --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
adrastogi
changed the title
adrastogi
force-pushed
the
adrastogi/cherry-pick-editor-compile
branch
from
9984c33 to
0730bc5
Compare
Contributor
Author
|
DML tests are the same failures seen when setting up the branch (i.e. unrelated to this payload). 2026-04-17T01:52:01.1938650Z 2: [ FAILED ] MeanVarianceNormalizationTest.DefaultAxes (Logs from ingesting the version change prior to the cherry-pick payload are here) |
skottmckay
approved these changes
Apr 17, 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:
Also took an isolated change to
base_tester.ccfrom here to avoid a unit test failure.