[be] Add SimpleFakeQuantize for QAT #114
Closed
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
facebook-github-bot
added
the
CLA Signed
jerryzh168
reviewed
Apr 3, 2024
Summary: This commit adds a simpler version of toq.FakeQuantize to be used for various flavors of QAT. In the future we should deprecate toq.FakeQuantize in favor of this new class. Test Plan: python test/quantization/test_qat_quant_api.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar
jerryzh168
reviewed
Apr 3, 2024
Comment on lines
+61
to
+66
| observer_attrs = [ | ||
| "ch_axis", "dtype", "qscheme", "quant_min", "quant_max", | ||
| "eps", "is_dynamic", "scale", "zero_point", | ||
| ] | ||
| if name in observer_attrs: | ||
| return getattr(self.observer, name) |
There was a problem hiding this comment.
maybe just use if hasattr(self,observer, name) instead of hardcoding
jerryzh168
reviewed
Apr 3, 2024
Comment on lines
+54
to
+55
| def calculate_qparams(self) -> Tuple[torch.Tensor, torch.Tensor]: | ||
| return self.observer.calculate_qparams() |
There was a problem hiding this comment.
we could potentially reroute function calls as well I think, maybe add a TODO here?
cpuhrsch
reviewed
Apr 3, 2024
| ) | ||
|
|
||
|
|
||
| class SimpleFakeQuantize(FakeQuantizeBase): |
There was a problem hiding this comment.
Do we have docs on what an Observer and a fake quant op is?
cpuhrsch
requested changes
Apr 3, 2024
|
Closing after some offline discussions. We'll put all observation/fq logic in the linear module itself so we don't need another class. |
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
Update readme Update README.md (pytorch#113) update README.md Update README.md (pytorch#114) Update README.md (pytorch#115) Update Readme.md
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.
Summary: This commit adds a simpler version of toq.FakeQuantize to be used for various flavors of QAT. In the future we should deprecate toq.FakeQuantize in favor of this new class.
Test Plan:
python test/quantization/test_qat_quant_api.py
Reviewers: jerryzh168
Subscribers: jerryzh168, supriyar