Skip to content

[ET Device Support] Propagate device info from TensorSpec into serialized Tensor#18079

Merged
Gasoonjia merged 14 commits intogh/gasoonjia/136/basefrom
gh/gasoonjia/136/head
Apr 14, 2026
Merged

[ET Device Support] Propagate device info from TensorSpec into serialized Tensor#18079
Gasoonjia merged 14 commits intogh/gasoonjia/136/basefrom
gh/gasoonjia/136/head

Conversation

@Gasoonjia
Copy link
Copy Markdown
Contributor

@Gasoonjia Gasoonjia commented Mar 10, 2026

…ized Tensor

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Mar 10, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18079

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

✅ You can merge normally! (2 Unrelated Failures)

As of commit a3cd7ec with merge base 0bf3c51 (image):

BROKEN TRUNK - The following jobs 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.

@github-actions
Copy link
Copy Markdown

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Mar 15, 2026
…ized Tensor

Pull Request resolved: #18079

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.
ghstack-source-id: 352274088
@exported-using-ghexport

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Mar 17, 2026
…ized Tensor

Pull Request resolved: #18079

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.
ghstack-source-id: 353066933
@exported-using-ghexport

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
…into serialized Tensor"

Propagate device information from `TensorSpec.device` (set by `PropagateDevicePass`) to
the serialized `schema.Tensor` in the emitted PTE file, to make runtime further aware of it.

Differential Revision: [D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Apr 14, 2026
…ensorSpecs (#18078)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #18080
* #18328
* #18079
* __->__ #18078

Add end-to-end device type annotation support from export to runtime.
Currently we only support one device per graph

The overall pipeline is:
a. Partitioner use `compile_spec` to determine which device the
partitoned blob is runing on
b. after lowered partitioned graph to backend, the new-introed
propagate_device_pass will annotate the input and output tensors of
delegate blob as target device.

Differential Revision:
[D95842511](https://our.internmc.facebook.com/intern/diff/D95842511/)
@Gasoonjia Gasoonjia merged commit d0bed94 into gh/gasoonjia/136/base Apr 14, 2026
162 of 164 checks passed
@Gasoonjia Gasoonjia deleted the gh/gasoonjia/136/head branch April 14, 2026 20:57
@Gasoonjia Gasoonjia temporarily deployed to cherry-pick-bot April 14, 2026 20:57 — with GitHub Actions Inactive
Gasoonjia added a commit that referenced this pull request Apr 14, 2026
…ized Tensor (#18894)

This PR was created by the merge bot to help merge the original PR into
the main branch.
ghstack PR number: #18079 by
@Gasoonjia
^ Please use this as the source of truth for the PR details, comments,
and reviews
ghstack PR base:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/136/base
ghstack PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/136/head
Merge bot PR base:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/135/orig
Merge bot PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/136/orig
Differential Revision:
[D95899706](https://our.internmc.facebook.com/intern/diff/D95899706/)
@diff-train-skip-merge

---------

Co-authored-by: gasoonjia <gasoonjia@icloud.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported meta-exported

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants