[kernel] Add template based unboxing#1284
Closed
larryliu0820 wants to merge 11 commits intogh/larryliu0820/6/basefrom
Closed
[kernel] Add template based unboxing#1284larryliu0820 wants to merge 11 commits intogh/larryliu0820/6/basefrom
larryliu0820 wants to merge 11 commits intogh/larryliu0820/6/basefrom
Conversation
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/1284
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 84e9d77 with merge base 02edc9e ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
larryliu0820
added a commit
that referenced
this pull request
Nov 23, 2023
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: 5163fd1
Pull Request resolved: #1284
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Nov 23, 2023
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: c82dc20
Pull Request resolved: #1284
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Nov 23, 2023
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: c430da1
Pull Request resolved: #1284
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
Feb 19, 2024
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: c430da1
Pull Request resolved: #1284
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
This was referenced Feb 29, 2024
larryliu0820
added a commit
that referenced
this pull request
Feb 29, 2024
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: f3f3dc2
Pull Request resolved: #1284
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
iseeyuan
approved these changes
Mar 2, 2024
Contributor
iseeyuan
left a comment
There was a problem hiding this comment.
LGTM.
Is there any plan to add template selective registration in future?
larryliu0820
added a commit
that referenced
this pull request
Mar 7, 2024
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: 119e9ae
Pull Request resolved: #1284
Contributor
Author
My intention was not to add it in the first version for simplicity. We can add it later |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: a5437bb
Pull Request resolved: #1284
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
larryliu0820
added a commit
that referenced
this pull request
Mar 12, 2024
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: ffda42c
Pull Request resolved: #1284
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
1 similar comment
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
Differential Revision: [D51553099](https://our.internmc.facebook.com/intern/diff/D51553099)
[ghstack-poisoned]
Contributor
Author
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Contributor
|
@larryliu0820 merged this pull request in 75284d2. |
kedarnath03
pushed a commit
to kedarnath03/executorch
that referenced
this pull request
Jun 25, 2025
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: e9c36de
Pull Request resolved: pytorch/executorch#1284
kedarnath03
pushed a commit
to kedarnath03/executorch
that referenced
this pull request
Jun 25, 2025
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
```
Tensor& my_op(RuntimeContext& ctx, const Tensor& self, const Tensor& other, Tensor& out) {
// ...
return out;
}
Kernel my_kernel = Kernel.make_boxed_kernel("my_ns::my_op",EXECUTORCH_FN(my_op));
register_kernels({my_kernel});
```
ghstack-source-id: 119e9ae
Pull Request resolved: pytorch/executorch#1284
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
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.
Stack from ghstack (oldest at bottom):
Adding a new feature to allow users to bypass codegen and register their
kernels directly. This is very useful for custom kernels for custom ops.
Example usage:
Differential Revision: D51553099