[QNN EP] Handle 0-dim tensor for Concat. #26644
Open
+40
−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
edgchen1
reviewed
Dec 5, 2025
onnxruntime/core/providers/qnn/builder/opbuilder/base_op_builder.cc
Outdated
Show resolved
Hide resolved
minfhong-quic
force-pushed
the
dev/minfhong/qnn-0-dim
branch
from
8c9f700 to
21e4877
Compare
There may exsit tensor with 0-dim in shape, especially for Concat's inputs. Modify the base op builder to ignore such tensor during construction. Test: UT.
minfhong-quic
force-pushed
the
dev/minfhong/qnn-0-dim
branch
from
21e4877 to
7606323
Compare
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Outdated suggestions cannot be applied.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
Define a util function
IsNullNodeUnitIODefto check whether given tensor has 0-dim in shape. To restrict the impact, current implementation only skip constructing such tensor for Concat.Motivation and Context
There may exsit tensor with 0-dim in shape, especially for Concat's inputs. Such null inputs often exist in models saved from PyTorch. Since QNN could not execute empty tensors, they must be explicitly handled.