Add option to disable fake quant for 8da4w QAT #198
Merged
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Outdated suggestions cannot be applied.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.
Summary: This feature helps with model convergence during QAT. The user can disable observation/fake quant for the first N steps and renable them later, allowing the activation and weight values to stabilize before applying quantization.
Test Plan:
python test/quantization/test_qat.py -k test_qat_8da4w_quantizer_disable_fake_quant
python test/quantization/test_qat.py -k test_qat_8da4w_quantizer_disable_fake_quant_backward
Reviewers: jerryzh168, cpuhrsch
Subscribers: jerryzh168, cpuhrsch, supriyar