[QNN-EP] Fix the input order in gen_qnn_ctx_onn_model.py #25090
+38
−40
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
chuteng-quic
changed the title
There was a problem hiding this comment.
Pull Request Overview
This PR addresses the incorrect ordering of inputs in the generated ONNX model by sorting tensor entries by their id rather than relying on the JSON file order. Key changes include updating the constructor of QnnTensorStruct to accept additional parameters (including id), enforcing key presence in the JSON parsing logic, and sorting both input and output tensors by their id.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
Description
In the original script, the order of inputs in the generated ONNX model follows the order in the JSON file instead of the id.
Therefore, the script will first sort the inputs by ID before wrapping the context into the new model.
Motivation and Context
If we use gen_qnn_ctx_onnx_model.py, it will wrap the context based on the order in qnn_model_net.json instead of the id in qnn_model_net.json, which may result in the onnx model having an incorrect order of inputs.