Add wrapper code to wrap an ET kernel into an ATen kernel#2186
Closed
larryliu0820 wants to merge 16 commits intogh/larryliu0820/20/basefrom
Closed
Add wrapper code to wrap an ET kernel into an ATen kernel#2186larryliu0820 wants to merge 16 commits intogh/larryliu0820/20/basefrom
larryliu0820 wants to merge 16 commits intogh/larryliu0820/20/basefrom
Conversation
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2186
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit d12ab2c with merge base e2b733e ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Feb 29, 2024
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
zou3519
reviewed
Mar 1, 2024
extension/aten_util/test/make_aten_functor_from_et_functor_test.cpp
Outdated
Show resolved
Hide resolved
iseeyuan
reviewed
Mar 2, 2024
iseeyuan
reviewed
Mar 2, 2024
Contributor
iseeyuan
left a comment
There was a problem hiding this comment.
What types are mapped from ExecuTorch to ATen? Does it works for tensors, list and prim types? Please add what can be mapped and what cannot be mapped.
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 08efcb4 Pull Request resolved: #2186
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: ce0cc7a Pull Request resolved: #2186
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: e0da0f0 Pull Request resolved: #2186
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: cf5ce9f Pull Request resolved: #2186
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
lucylq
approved these changes
Mar 12, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
larryliu0820
added a commit
that referenced
this pull request
Mar 13, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 2ac8c4c Pull Request resolved: #2186
larryliu0820
added a commit
that referenced
this pull request
Mar 13, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: e8b0c10 Pull Request resolved: #2186
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 13, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 45d661f Pull Request resolved: #2186
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D54394149](https://our.internmc.facebook.com/intern/diff/D54394149) [ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 13, 2024
Summary: Add an API that is able to wrap ExecuTorch kernels into ATen kernels. This can save kernel author time, if they start from ExecuTorch kernels. In this PR we only support the following argument types to ExecuTorch kernels: * Tensor-like. `torch::executor::Tensor` and its reference/const reference. * Primitive types. `int` `float` etc. Doesn't support ArrayRef or Optional yet. Test Plan: Rely on unit tests Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 16d551a Pull Request resolved: #2186
Contributor
|
This pull request has been merged in 20f5073. |
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
5 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.
Stack from ghstack (oldest at bottom):
Summary:
Add an API that is able to wrap ExecuTorch kernels into ATen kernels.
This can save kernel author time, if they start from ExecuTorch kernels.
In this PR we only support the following argument types to ExecuTorch
kernels:
torch::executor::Tensorand its reference/constreference.
intfloatetc.Doesn't support ArrayRef or Optional yet.
Test Plan:
Rely on unit tests
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D54394149