Repository navigation
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23261
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled JobAs of commit 7eb92a3 with merge base d46a886 ( CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
|
|
Contributor
|
@RahulC7 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D120871768. |
This PR needs a
|
DrJessop
approved these changes
Sep 29, 2026
meta-codesync
Bot
changed the title
RahulC7
force-pushed
the
export-D120871768
branch
from
October 20, 2026 17:20
37456c1 to
4616348
Compare
RahulC7
added a commit
to RahulC7/executorch
that referenced
this pull request
Oct 20, 2026
…23261) Summary: ## Context The way we lowered the GDN model is we looked at the traced model, and then recreated "stages" of it(i.e created a graph for that stage), and lowered each one of those stages, making them go through the entire compiler pipeline. That’s usually fine for the ops/nodes in the middle, because they still have the surrounding nodes(producer consumer chain) and those get collapsed/changed in the same way, but in the boundaries, where there’s connections to other other nodes not in the subgraph, the lowering might end up producing a different result than what we expect in the actual graph. The quant/dequant insertion, calibration and FuseMul adjacency depend on the global context so it’ll look different. That's what happens here. ## Problem In D117100989, we do `N_c = -A_c` as `aten.full(-1.0) + aten.mul.Tensor`(elementwise kernel). However, before the multiply, there's a quantize, and so multiply gets combined with the quantize. The issue is that this is a negative, and so we're going to have a negative scale in the quantize/dequantize scales, because of `FuseMulTensorIntoDequantPass` and `FuseMulScalarIntoDequantPass` folding it in. ## What this diff does - Make all three multiply fusion passes stop when the derived scale is not positive. - Leave the original multiply in the graph when fusion is not valid. - Add focused tests for tensor-to-quant, tensor-from-dequant, and scalar-from-dequant with multipliers `0.0` and `-1.0`. - Give the chunk-32 GDN test a test-only gate offset of `-5.0`. This keeps the 32-step cumulative `Gamma_c` values in the useful int16 calibration range. Chunk size 2 stays unchanged. - Use measured tolerances for the three equivalent chunk-32 pre-trace transforms. ## Result The full chunk-32 graph keeps one explicit `aten.mul.Tensor` with `aten.full(-1.0)` for `N_c = -A_c`. All quantize, dequantize, requantize, and packed prep scales in the dumped graph are finite and positive. Reviewed By: ThomasJannaud Differential Revision: D120871768
…23261) Summary: Pull Request resolved: pytorch#23261 ## Context The way we lowered the GDN model is we looked at the traced model, and then recreated "stages" of it(i.e created a graph for that stage), and lowered each one of those stages, making them go through the entire compiler pipeline. That’s usually fine for the ops/nodes in the middle, because they still have the surrounding nodes(producer consumer chain) and those get collapsed/changed in the same way, but in the boundaries, where there’s connections to other other nodes not in the subgraph, the lowering might end up producing a different result than what we expect in the actual graph. The quant/dequant insertion, calibration and FuseMul adjacency depend on the global context so it’ll look different. That's what happens here. ## Problem In D117100989, we do `N_c = -A_c` as `aten.full(-1.0) + aten.mul.Tensor`(elementwise kernel). However, before the multiply, there's a quantize, and so multiply gets combined with the quantize. The issue is that this is a negative, and so we're going to have a negative scale in the quantize/dequantize scales, because of `FuseMulTensorIntoDequantPass` and `FuseMulScalarIntoDequantPass` folding it in. ## What this diff does - Make all three multiply fusion passes stop when the derived scale is not positive. - Leave the original multiply in the graph when fusion is not valid. - Add focused tests for tensor-to-quant, tensor-from-dequant, and scalar-from-dequant with multipliers `0.0` and `-1.0`. - Give the chunk-32 GDN test a test-only gate offset of `-5.0`. This keeps the 32-step cumulative `Gamma_c` values in the useful int16 calibration range. Chunk size 2 stays unchanged. - Use measured tolerances for the three equivalent chunk-32 pre-trace transforms. ## Result The full chunk-32 graph keeps one explicit `aten.mul.Tensor` with `aten.full(-1.0)` for `N_c = -A_c`. All quantize, dequantize, requantize, and packed prep scales in the dumped graph are finite and positive. Reviewed By: ThomasJannaud Differential Revision: D120871768
RahulC7
force-pushed
the
export-D120871768
branch
from
October 20, 2026 17:23
4616348 to
7eb92a3
Compare
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:
What this diff does
0.0and-1.0.Result
The full chunk-32 graph keeps one explicit
aten.mul.Tensorwithaten.full(-1.0)forN_c = -A_c. All quantize, dequantize, requantize, and packed prep scales in the dumped graph are finite and positive.Reviewed By: ThomasJannaud
Differential Revision: D120871768