Repository navigation
Conversation
…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. ] Differential Revision: D127746753
Summary: `pow.Tensor_Scalar(int32, 2.0)` returns float32, but the `mul.Tensor(x, x)` chain that `ReplacePowWithMulPass` emits stays int32. The pass copied the float32 `meta` onto the int32 `mul` nodes, so the lowered program's output dtype no longer matched the eager reference. The pass now gives up when the input dtype differs from the `pow` output dtype. Found by the Jarvis nightly operator tests: `test_pow_Tensor_Scalar_out` cases 14 and 23 (int32 input, exponent 2.0) fail on nxp, DLA, Artemis v3/v4 and CPU with `The label tensor ... dtype shall be torch.int32, but now is torch.float32`. Differential Revision: D127746754
Summary: `div.Tensor_mode(a, b, rounding_mode=None)` is true division. The HiFi `div_out_mode` sent `None` to the non-optimized path, where `mode_is_trunc` was false and the code fell through to `floor_divide` (its comment assumed the mode "must be floor"). So `7 / 2` returned 3 and `-7 / 2` returned -4. The kernel now delegates to `div_out` when `mode` has no value, which is what the portable and Fusion G3 `div_out_mode` already do. Found by the Jarvis nightly operator tests: on nxp_rt600 (HiFi4), `test_aten_div_out_mode` fails every case where FACTO picks `rounding_mode=None` (25 of 50, all with `max_abs_diff ≈ 0.99`). DLA, which uses a different kernel, passes all 50. Differential Revision: D127746755
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24178
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 817eeeb with merge base a90db24 ( 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 D127746755. |
This PR needs a
|
ethansfng
approved these changes
Oct 27, 2026
This branch was successfully 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:
div.Tensor_mode(a, b, rounding_mode=None)is true division. The HiFidiv_out_modesentNoneto the non-optimized path, wheremode_is_truncwas false and the code fell through tofloor_divide(its comment assumed the mode "must be floor"). So7 / 2returned 3 and-7 / 2returned -4. The kernel now delegates todiv_outwhenmodehas no value, which is what the portable and Fusion G3div_out_modealready do.Found by the Jarvis nightly operator tests: on nxp_rt600 (HiFi4),
test_aten_div_out_modefails every case where FACTO picksrounding_mode=None(25 of 50, all withmax_abs_diff ≈ 0.99). DLA, which uses a different kernel, passes all 50.Differential Revision: D127746755