Repository navigation
Move positional alpha to kwargs in ReplaceScalarWithTensorArgPass (#24176) - #24176
Merged
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24176
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 9e147d7 with merge base bf9bef3 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@aliafzal has exported this pull request. If you are a Meta employee, you can view the originating Diff in D127746753. |
This PR needs a
|
ethansfng
approved these changes
Oct 27, 2026
DrJessop
approved these changes
Oct 27, 2026
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Oct 28, 2026
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now passes `args[:2]` and moves `alpha` into `kwargs`, so `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Found by the Jarvis nightly operator tests: `test_aten_add_scalar_out` fails 13 of 24 FACTO cases (every case with an explicit `alpha`) on nxp, DLA and Artemis v3/v4. ] Reviewed By: DrJessop Differential Revision: D127746753
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Oct 28, 2026
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now passes `args[:2]` and moves `alpha` into `kwargs`, so `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Found by the Jarvis nightly operator tests: `test_aten_add_scalar_out` fails 13 of 24 FACTO cases (every case with an explicit `alpha`) on nxp, DLA and Artemis v3/v4. ] Reviewed By: DrJessop Differential Revision: D127746753
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Oct 28, 2026
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now passes `args[:2]` and moves `alpha` into `kwargs`, so `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Found by the Jarvis nightly operator tests: `test_aten_add_scalar_out` fails 13 of 24 FACTO cases (every case with an explicit `alpha`) on nxp, DLA and Artemis v3/v4. ] Reviewed By: DrJessop Differential Revision: D127746753
aliafzal
force-pushed
the
export-D127746753
branch
from
October 28, 2026 07:39
fd4fbd3 to
1e43d66
Compare
aliafzal
force-pushed
the
export-D127746753
branch
from
October 28, 2026 20:33
1e43d66 to
b5303f7
Compare
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Oct 28, 2026
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now binds the call by name with `torch.fx.operator_schemas.normalize_function` (the part of `get_arg` that doesn't need a `Node`; `call_operator` gets no node), passes `self` (`input` after normalization) and `other` positionally, and `alpha` as a kwarg. `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Authored with Claude Code. Reviewed By: DrJessop Differential Revision: D127746753
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Oct 28, 2026
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now binds the call by name with `torch.fx.operator_schemas.normalize_function` (the part of `get_arg` that doesn't need a `Node`; `call_operator` gets no node), passes `self` (`input` after normalization) and `other` positionally, and `alpha` as a kwarg. `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Authored with Claude Code. Reviewed By: DrJessop Differential Revision: D127746753
…torch#24176) Summary: `add.Scalar(Tensor self, Scalar other, Scalar alpha=1)` takes `alpha` positionally, but `add.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)` takes it as keyword-only, and the same holds for `sub`. When `alpha` was the third positional argument, `get_replacement` passed it through `*args[2:]`, and building the `.Tensor` node raised `RuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given`. The 3-argument path now binds the call by name with `torch.fx.operator_schemas.normalize_function` (the part of `get_arg` that doesn't need a `Node`; `call_operator` gets no node), passes `self` (`input` after normalization) and `other` positionally, and `alpha` as a kwarg. `get_replacement` always gets 2 args and no longer forwards extra ones. The Arm `ReplaceScalarWithTensorByProfilePass` subclass routes through the same base `call_operator`, so it gets the fix too for edge `add/sub.Scalar`. `torch.ops.aten.add/sub.Scalar` with a positional `alpha` still pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected. Authored with Claude Code. Reviewed By: DrJessop Differential Revision: D127746753
aliafzal
force-pushed
the
export-D127746753
branch
from
October 28, 2026 20:57
b5303f7 to
9e147d7
Compare
meta-codesync
Bot
changed the title
This branch was previously deployed
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
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:
add.Scalar(Tensor self, Scalar other, Scalar alpha=1)takesalphapositionally, butadd.Tensor(Tensor self, Tensor other, *, Scalar alpha=1)takes it as keyword-only, and the same holds forsub. Whenalphawas the third positional argument,get_replacementpassed it through*args[2:], and building the.Tensornode raisedRuntimeError: aten::add() takes 2 positional argument(s) but 3 was/were given. The 3-argument path now binds the call by name withtorch.fx.operator_schemas.normalize_function(the part ofget_argthat doesn't need aNode;call_operatorgets no node), passesself(inputafter normalization) andotherpositionally, andalphaas a kwarg.get_replacementalways gets 2 args and no longer forwards extra ones. The ArmReplaceScalarWithTensorByProfilePasssubclass routes through the same basecall_operator, so it gets the fix too for edgeadd/sub.Scalar.torch.ops.aten.add/sub.Scalarwith a positionalalphastill pass through unreplaced, as before. The changed path previously always raised, so no graph that worked before is affected.Authored with Claude Code.
Reviewed By: DrJessop
Differential Revision: D127746753