Add small repro test for unsigned -> signed et loss error #8506
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/8506
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 Unrelated FailureAs of commit 13a997c with merge base c00c798 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D69668881 |
dulinriley
force-pushed
the
export-D69668881
branch
from
79dff9a to
60b0255
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69668881 |
|
@pytorchbot label "topic: not user facing" |
sabarishsnk
approved these changes
Feb 15, 2025
sabarishsnk
approved these changes
Feb 15, 2025
skrtskrtfb
approved these changes
Feb 15, 2025
dulinriley
added a commit
to dulinriley/executorch
that referenced
this pull request
Feb 18, 2025
Summary: There was a difference in behavior from `quantized_decomposed.quantize_per_tensor` and `cadence.quantize_per_tensor`, specifically how rounding half values worked. The former rounds towards even (based on `torch.round` which does that). The latter rounds away from zero. Make sure the python implementation matches the Executorch implementation in this regard. Reviewed By: sabarishsnk Differential Revision: D69668881
dulinriley
force-pushed
the
export-D69668881
branch
from
60b0255 to
c364a2c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69668881 |
Summary: There was a difference in behavior from `quantized_decomposed.quantize_per_tensor` and `cadence.quantize_per_tensor`, specifically how rounding half values worked. The former rounds towards even (based on `torch.round` which does that). The latter rounds away from zero. Make sure the python implementation matches the Executorch implementation in this regard. Reviewed By: sabarishsnk Differential Revision: D69668881
dulinriley
force-pushed
the
export-D69668881
branch
from
c364a2c to
13a997c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69668881 |
dbort
reviewed
Feb 19, 2025
| @@ -16,6 +16,9 @@ | |||
| from numbers import Number | |||
| from typing import cast, Sequence | |||
|
|
|||
| # Import these for the cadence function signatures. | |||
| import executorch.backends.cadence.aot.ops_registrations # noqa: F401 | |||
There was a problem hiding this comment.
This line broke the linter job: https://github.com/pytorch/executorch/actions/runs/13398623818/job/37423762070#step:15:7593
I think it needs two spaces before the #. Please run lintrunner -a to fix this, and make sure that the job is passing before merging PRs.
dbort
added a commit
that referenced
this pull request
Feb 19, 2025
Fix lint issue in backends/cadence/aot/fuse_ops.py introduced in #8506
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:
There was a difference in behavior from
quantized_decomposed.quantize_per_tensorand
cadence.quantize_per_tensor, specifically how rounding half values worked.The former rounds towards even (based on
torch.roundwhich does that).The latter rounds away from zero.
Make sure the python implementation matches the Executorch implementation in this
regard.
Differential Revision: D69668881