Cortex_M backend: Remove int8 requirement for zero_points #16061
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
The zero point would sometimes get out of range in the hardswish decomposition (depending on the range of the quantized output) as it adjusts the zero point. Since the zero_point is applied in int32 accumulation there is no actual reason for the limitation, so we can just remove it. Additionally change the input to linear_hardswish to reliably trigger the behaviour causing the crash before the fix was introduced to catch future regressions. Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ia300d57acd2f3e63f49bdf1bc8664da8a3f49bf9
AdrianLundell
added
partner: arm
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16061
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit a12b0e0 with merge base 1d35df2 ( NEW FAILURE - The following job has 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. |
meta-cla
bot
added
the
CLA Signed
Collaborator
Author
|
Test failures unrelated |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
The zero point would sometimes get out of range in the hardswish decomposition (depending on the range of the quantized output) as it adjusts the zero point. Since the zero_point is applied in int32 accumulation there is no actual reason for the limitation, so we can just remove it.
Additionally change the input to linear_hardswish to reliably trigger the behaviour causing the crash before the fix was introduced to catch future regressions.
cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai