NXP backend: Use default (non-shared) quantization params for HardTanh #12893
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12893
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit bb7d8ce with merge base 4197fc1 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
I created issues for the two introduced TODOs: |
StrycekSimon
force-pushed
the
upstream/main-nxp/EIEX-407-upstream-non-shared-quantization-for-hardtanh
branch
from
614da96 to
effe5e9
Compare
|
@pytorchbot label "release notes: nxp" |
pytorch-bot
bot
added
the
release notes: nxp
robert-kalmar
force-pushed
the
upstream/main-nxp/EIEX-407-upstream-non-shared-quantization-for-hardtanh
branch
from
c35e001 to
e4445ff
Compare
|
Although correct for case, when the HardTanh is isolated, so approve to merge it (given the test passes). But we must resolve the Conv/Matmul + Activation quantization better - #13063. |
| @pytest.mark.parametrize( | ||
| "activation_range", list(HardTanhConverter.supported_modes_map.keys()) | ||
| ) | ||
| @pytest.mark.parametrize("inplace", [True, False]) | ||
| def test_custom_hardtanh_quant( | ||
| mocker, input_shape: tuple[int], activation_range: tuple[int, int], inplace: bool | ||
| ): | ||
| # TODO: This test suffers from non-ideal testing random quantization, because we always use range <0,1>. |
robert-kalmar
approved these changes
Aug 1, 2025
robert-kalmar
force-pushed
the
upstream/main-nxp/EIEX-407-upstream-non-shared-quantization-for-hardtanh
branch
from
e4445ff to
bb7d8ce
Compare
robert-kalmar
deleted the
upstream/main-nxp/EIEX-407-upstream-non-shared-quantization-for-hardtanh
branch
agrima1304
pushed a commit
to agrima1304/executorch
that referenced
this pull request
Aug 26, 2025
…pytorch#12893) ### Summary Replaces shared quantization parameters specs for standard `QuantizationSpec` in HardTanh operator. ### Test plan Unit test files update to correspond to this change. cc @skywall Co-authored-by: Lukas Sztefek <[email protected]>
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
Replaces shared quantization parameters specs for fixed ones in HardTanh operator.
Test plan
Existing unit test files were updated to correspond to this change.
cc @skywall