Walk transparent ops when extracting input quant params (#20139)#20139
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20139
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 2795439 with merge base f0dff03 ( BROKEN TRUNK - The following job 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
Contributor
|
@ethansfng has exported this pull request. If you are a Meta employee, you can view the originating Diff in D107922730. |
This PR needs a
|
meta-codesync
Bot
changed the title
ethansfng
force-pushed
the
export-D107922730
branch
from
e9b1f53 to
2304b88
Compare
ethansfng
added a commit
to ethansfng/executorch
that referenced
this pull request
Jun 9, 2026
Summary: SAM 3's encoder input feeds a transparent shape op first — placeholder → reshape (patchify) → quantize_per_tensor — whereas the original code only recognized placeholder → quantize_per_tensor (a quantize directly on the input). The change walks through transparent ops (reshape/permute/transpose/etc.) from the input to reach the first quantize, so that indirected pattern resolves. Differential Revision: D107922730
ethansfng
added a commit
to ethansfng/executorch
that referenced
this pull request
Jun 9, 2026
Summary: SAM 3's encoder input feeds a transparent shape op first — placeholder → reshape (patchify) → quantize_per_tensor — whereas the original code only recognized placeholder → quantize_per_tensor (a quantize directly on the input). The change walks through transparent ops (reshape/permute/transpose/etc.) from the input to reach the first quantize, so that indirected pattern resolves. Differential Revision: D107922730
ethansfng
force-pushed
the
export-D107922730
branch
from
2304b88 to
710cea4
Compare
mcremon-meta
approved these changes
Jun 9, 2026
Summary: SAM 3's encoder input feeds a transparent shape op first — placeholder → reshape (patchify) → quantize_per_tensor — whereas the original code only recognized placeholder → quantize_per_tensor (a quantize directly on the input). The change walks through transparent ops (reshape/permute/transpose/etc.) from the input to reach the first quantize, so that indirected pattern resolves. Reviewed By: DrJessop Differential Revision: D107922730
ethansfng
force-pushed
the
export-D107922730
branch
from
710cea4 to
2795439
Compare
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
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.
Summary:
SAM 3's encoder input feeds a transparent shape op first — placeholder → reshape (patchify) → quantize_per_tensor — whereas the original code only recognized placeholder → quantize_per_tensor (a quantize directly on the input). The change walks through transparent ops (reshape/permute/transpose/etc.) from the input to reach the first quantize, so that indirected pattern resolves.
Reviewed By: DrJessop
Differential Revision: D107922730