Cortex_m backend: Add SharedQspecQuantizer + maximum/minimum #15872
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
This patch reworks how ops w/o rescaling are handled. Instead of not annotating them and counting on the retracing to make them get correct dtype, they must now be annotated by the SharedQspecQuantizer. The reason for this is that it simplifies ensuring that non-rescaling with multiple inputs has the same scale on both inputs. It also becomes easier to tell which dtype each op will receive before folding. Signed-off-by: Adrian Lundell <[email protected]> Change-Id: I99c9e8b11fbb278e50c90ec4915b1347337efafa
AdrianLundell
added
the
partner: arm
AdrianLundell
requested review from
kirklandsign and
larryliu0820
as code owners
AdrianLundell
added
the
release notes: none
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15872
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit 01f7e97 with merge base 2f9e574 ( BROKEN TRUNK - The following jobs 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
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Outdated suggestions cannot be applied.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.
This patch reworks how ops w/o rescaling are handled. Instead of not annotating them and counting on the retracing to make them get correct dtype, they must now be annotated by the SharedQspecQuantizer.
The reason for this is that it simplifies ensuring that non-rescaling with multiple inputs has the same scale on both inputs. It also becomes easier to tell which dtype each op will receive before folding.
cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai