OVInferRequest::SetTensor: Set tensor upon cached_binding shape mismatch - #783
Merged
sfatimar merged 1 commit intoAug 21, 2025
Conversation
sfatimar
approved these changes
Aug 21, 2025
|
@RyanMetcalfeInt8 please mention JIRA ID here |
Author
There isn't one. |
vthaniel
pushed a commit
that referenced
this pull request
Aug 28, 2025
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
SetTensor previously only accounted for tensor ptr value to decide whether it needed to actually call
ovInfReq.set_tensor. But this is problematic, as the user app can wrap a buffer with ORT tensors of differing shapes between different calls to session.run.For this cache binding feature, we also need to take into account shape.