[Fixed]: Onnx function transform error in onnx ptq #3260
Conversation
This file contains 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
|
@kshpv , please take a look |
|
@thinvy thanks for raising the issue. Could you provide more details on the scenario where you encountered it? Did this fix completely resolve the problem? I am wondering whether the model that you mentioned having function inside would be handled correctly by quantization algorithm. |
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Outdated suggestions cannot be applied.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.
Changes
Added the function member transfer when constructing the _insert_outputs onnx model.
Reason for changes
Onnx function is a widely used new feature. In 'torch.onnx.dynamo_export' and 'torch.onnx.export' ('export_modules_as_functions' param), some user modules will be converted to onnx functions. However, the current nncf onnx quantization does not do special processing for it, resulting in the onnx exported by this function converting the user's onnx function into an unimplemented custom operator, causing errors in the subsequent ptq process.