-
Notifications
You must be signed in to change notification settings - Fork 713
Add hardsigmoid operator to Arm backend #8091
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
* Add filter_fn to ops_to_not_decompose, to filter out quantized candidate ops * Added aten.hardsigmoid as a table op for the BI case Signed-off-by: Tom Allsop <tom.allsop@arm.com> Change-Id: I67e6d256dfae6ec6b8f679598043054d25d4a6de
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8091
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 2 Pending, 1 Unrelated FailureAs of commit 0ea3aed with merge base c9f5f19 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
macos job fail not related |
This is something we are trying to fix. But running into other issues. Sorry about that. |
| self, | ||
| ep: ExportedProgram, | ||
| ) -> Tuple[List[torch._ops.OpOverload], Optional[Callable[[torch.fx.Node], bool]]]: | ||
| ops_to_not_decompose_if_quant_op = [ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nit: why another list?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This list is for ops where we specifically only want to not decompose if it's quantized. Also, another operator will be coming in a follow on commit, so a list is needed
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I see that you are using the same list in the filter_fn, sounds good, false alarm.
Signed-off-by: Tom Allsop tom.allsop@arm.com
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218