Allow context-binary lowering to use edge dialect ops (#20518)#20518
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20518
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ No FailuresAs of commit efc6e3c with merge base 47fd0d8 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D109598309. |
This PR needs a
|
meta-codesync
Bot
changed the title
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jun 25, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
June 25, 2026 17:01
ce774b0 to
101ea39
Compare
JakeStevens
added
the
module: qnn
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jun 25, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
June 25, 2026 19:10
101ea39 to
e924d07
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 6, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 6, 2026 18:08
e924d07 to
1095873
Compare
psiddh
requested review from
chenweng-quic,
haowhsu-quic,
shewu-quic and
winskuo-quic
July 6, 2026 22:49
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 7, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 7, 2026 00:46
1095873 to
18d165e
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 7, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 7, 2026 18:08
18d165e to
36aeffe
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 7, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. Loader detection now goes through a single `is_context_loader_target()` helper that matches the op namespace (so it works on the edge-dialect wrapper), replacing the three name-dependent checks (`eval`, raw `.namespace`, substring). Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 7, 2026 18:16
36aeffe to
9daf0b4
Compare
shewu-quic
reviewed
Jul 9, 2026
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 14, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
2 times, most recently
from
July 14, 2026 20:59
8b08c87 to
b249858
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 14, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 14, 2026
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 14, 2026 21:02
b3fde42 to
e39dbfd
Compare
Contributor
Author
|
Addressed claude review |
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 14, 2026
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 14, 2026 21:06
e39dbfd to
db9263c
Compare
Contributor
Author
|
@harshs-qti @shewu-quic are there any specific concerns you have or additional tests I can run? |
psiddh
approved these changes
Jul 16, 2026
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 16, 2026 13:39
db9263c to
d0a50d0
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 16, 2026 13:42
d0a50d0 to
69c7589
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 16, 2026 15:26
69c7589 to
ee75fa2
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 16, 2026 15:30
ee75fa2 to
939b640
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
2 times, most recently
from
July 16, 2026 15:30
22a970b to
939b640
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 16, 2026
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 16, 2026 15:35
939b640 to
151c181
Compare
JakeStevens
added a commit
to JakeStevens/executorch
that referenced
this pull request
Jul 17, 2026
Summary: Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 17, 2026 14:52
151c181 to
11362e4
Compare
Summary: Pull Request resolved: pytorch#20518 Unblocks the QNN context-binary path from lowering through `to_edge` with `_use_edge_ops=True` (the default). Previously it was pinned to `EdgeCompileConfig(_use_edge_ops=False)` purely to keep the `qaisw` context-loader custom op's original name, because loader detection was name-based. We can simply unwrap the op overload and maintain the same check. Reviewed By: rascani Differential Revision: D109598309
JakeStevens
force-pushed
the
export-D109598309
branch
from
July 17, 2026 14:55
11362e4 to
efc6e3c
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
4 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:
Unblocks the QNN context-binary path from lowering through
to_edgewith_use_edge_ops=True(the default). Previously it was pinned toEdgeCompileConfig(_use_edge_ops=False)purely to keep theqaiswcontext-loader custom op's original name, because loader detection was name-based.We can simply unwrap the op overload and maintain the same check.
Reviewed By: rascani
Differential Revision: D109598309