Enable strongly typed ops for deployment #13230
Merged
+471
−4
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13230
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 Unrelated FailureAs of commit ea124be with merge base 0e76a97 ( NEW FAILURES - The following jobs have failed:
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
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
This PR needs a
|
msluszniak
reviewed
Aug 8, 2025
| #include <executorch/backends/cadence/hifi/kernels/kernels.h> | ||
| #include <executorch/runtime/kernel/kernel_includes.h> | ||
|
|
||
| namespace cadence { |
There was a problem hiding this comment.
Nested namespaces with :: are prefered since c++17, https://clang.llvm.org/extra/clang-tidy/checks/modernize/concat-nested-namespaces.html
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
mcremon-meta
added a commit
that referenced
this pull request
Aug 9, 2025
Summary: Pull Request resolved: #13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Differential Revision: D79867630
mcremon-meta
force-pushed
the
export-D79867630
branch
from
4bd5b3b to
007022b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
mcremon-meta
added a commit
that referenced
this pull request
Aug 9, 2025
Summary: Pull Request resolved: #13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Differential Revision: D79867630
mcremon-meta
force-pushed
the
export-D79867630
branch
from
007022b to
368ca27
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
mcremon-meta
added a commit
that referenced
this pull request
Aug 9, 2025
Summary: Pull Request resolved: #13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Differential Revision: D79867630
mcremon-meta
force-pushed
the
export-D79867630
branch
from
368ca27 to
a7f91c5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
mcremon-meta
added a commit
that referenced
this pull request
Aug 11, 2025
Summary: Pull Request resolved: #13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Differential Revision: D79867630
mcremon-meta
force-pushed
the
export-D79867630
branch
from
a7f91c5 to
9fba6c6
Compare
zonglinpeng
approved these changes
Aug 12, 2025
ethansfng
pushed a commit
to ethansfng/executorch
that referenced
this pull request
Aug 12, 2025
Summary: Pull Request resolved: pytorch#13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Differential Revision: D79867630
Summary: Pull Request resolved: #13230 As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor. This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later! Reviewed By: zonglinpeng Differential Revision: D79867630
|
This pull request was exported from Phabricator. Differential Revision: D79867630 |
mcremon-meta
force-pushed
the
export-D79867630
branch
from
9fba6c6 to
ea124be
Compare
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:
As titled. This allows a severe reduction in codesize by only using the bare minimum cpp code. Right now, this diff only implements that option for quantized fully connected per tensor.
This diff is introducing opt level 4 to use for deployment purposes. The idea is similar to -Os in most compilers, we just use 4 for simplicity and because for now, everything should be inclusive by construction. This decision can be re-visited later!
Differential Revision: D79867630