[TorchFX] Bias fusing is removed from default transformations #3027
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Outdated suggestions cannot be applied.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
constant_folding
is updated to remove inplace operations without usersextract_model
is updated to support original model output as a subgraph outputReason for changes
To make it possible to apply quantization the same way it done by X86Quantizer
Related tickets
#2766
110985
Tests
test_constant_folding
andtest_constant_folding_with_constraints
are updated with a constant subgraph which contains an inplace op (relu_
)test_model_extraction_with_original_output
is introduced