Runtime API to retrieve attributes #10144
Merged
Conversation
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
JacobSzwejbka
requested review from
kirklandsign,
larryliu0820,
lucylq and
swolchok
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10144
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 61a05d8 with merge base d60d03e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
larryliu0820
approved these changes
Apr 14, 2025
Contributor
Author
|
@cptspacemanspiff We ended up pursuing this approach over the memory planning one to share state between entry points. I think this one is easier to maintain (fewer foot guns setting it up as well), though we can continue supporting both approaches. |
JacobSzwejbka
added
release notes: api
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
0a9afd3 to
a979474
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
a979474 to
25112d7
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
25112d7 to
6780249
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
6780249 to
0b29249
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Pull Request resolved: pytorch#10144 Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
2 times, most recently
from
78f72e0 to
522f839
Compare
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 14, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
e723876 to
962780b
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
1 similar comment
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Pull Request resolved: pytorch#10144 Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
962780b to
2a73d33
Compare
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
2a73d33 to
2c04ba2
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
2c04ba2 to
042c9b8
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Pull Request resolved: pytorch#10144 Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
042c9b8 to
256645b
Compare
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
256645b to
26cf1d0
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 15, 2025
Summary: Pull Request resolved: pytorch#10144 Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
2 times, most recently
from
a20bd6f to
7fe8391
Compare
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 17, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
added a commit
to JacobSzwejbka/executorch-1
that referenced
this pull request
Apr 17, 2025
Summary: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
7fe8391 to
53bf9ea
Compare
Summary: Pull Request resolved: pytorch#10144 Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary. Reviewed By: larryliu0820 Differential Revision: D72802654
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D72802654 |
JacobSzwejbka
force-pushed
the
export-D72802654
branch
from
53bf9ea to
61a05d8
Compare
keyprocedure
pushed a commit
to keyprocedure/executorch
that referenced
this pull request
Apr 21, 2025
Differential Revision: D72802654 Pull Request resolved: pytorch#10144
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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: Scan implementation today which is kind of slow. I dont think people wil regularly be scanning for tons of tensors though so perf is not super sensitive. Can always add a cache later if necessary.
Differential Revision: D72802654
cc @larryliu0820 @lucylq