[slimtensor] Add from_etensor factory function for ETensor to SlimTensor conversion #16551

Gasoonjia · 2026-01-12T23:18:35Z

Stack from ghstack (oldest at bottom):

Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device.

Key features:

Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t)
Supports CPU and CUDA target devices via storage()->copy_()
Preserves tensor strides (non-contiguous layouts)
Provides both reference and pointer overloads

Differential Revision: D90539554

…sor conversion Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

pytorch-bot · 2026-01-12T23:18:41Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16551

📄 Preview Python docs built from this PR

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

⏳ 42 Pending, 2 Unrelated Failures

As of commit 173572d with merge base 99348ed ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

Test Metal Backend / test-model-metal-e2e (openai, whisper-small, non-quantized) / macos-job (gh) (similar failure)
RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

BROKEN TRUNK - The following job failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

Test Metal Backend / test-model-metal-e2e (openai, whisper-large-v3-turbo, non-quantized) / macos-job (gh) (trunk failure)
RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

This comment was automatically generated by Dr. CI and updates every 15 minutes.

…sor conversion Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) ghstack-source-id: 333060891 Pull Request resolved: #16551

github-actions · 2026-01-12T23:19:20Z

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.

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

…sor conversion Pull Request resolved: #16551 Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads ghstack-source-id: 333062343 @exported-using-ghexport Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/)

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #16565 * #16551 * #16469 * #16457 * #16455 * #16454 * #16453 * #16452 * #16451 * #16450 * #16449 * #16448 * #16447 * #16446 * __->__ #16724 Copy CUDAGuard and CUDAStreamGuard from cuda/runtime/ to aoti/slim/cuda/ to support slimtensor requirement while get rid of potential circular dependency: - cuda_backend/main_functionalities -> aoti/slimtensor -> cuda_backend/cuda_guard This change: - copy guard.h, guard.cpp and test files from backend/cuda_backend to backend/aoti/slim/cuda/ Differential Revision: [D91056808](https://our.internmc.facebook.com/intern/diff/D91056808/)

…v2 (#16446) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #16565 * #16551 * #16469 * #16457 * #16455 * #16454 * #16453 * #16452 * #16451 * #16450 * #16449 * #16448 * #16447 * __->__ #16446 * #16724 Add SlimTensor-based implementations of AOTI shim functions for tensor creation: 1. `aoti_torch_create_tensor_from_blob_v2()` - Creates a non-owning SlimTensor that wraps existing memory using the `from_blob()` factory Both functions support CPU and CUDA devices and handle all 7 SlimTensor dtypes. Also add `memory_slim.h` and `memory_slim.cpp` with SlimTensor-based shim implementations for working on new API while not impact the current pipeline. Will use memory_slim.{h/cpp} to replace current memory.{h/cpp} when everything has been set up. Differential Revision: [D90126247](https://our.internmc.facebook.com/intern/diff/D90126247/)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #16565 * #16551 * #16469 * #16457 * #16455 * #16454 * #16453 * #16452 * #16451 * #16450 * #16449 * #16448 * __->__ #16447 * #16446 * #16724 Add SlimTensor-based implementations of AOTI shim functions for tensor creation: `aoti_torch_create_tensor_from_blob_v2()` - Creates a non-owning SlimTensor that wraps existing memory using the `from_blob()` factory Both functions support CPU and CUDA devices and handle all 7 SlimTensor dtypes. Changes: - Add `memory_slim.h` and `memory_slim.cpp` with SlimTensor-based shim implementations - Add `runtime_shims_slim` library target to TARGETS with `CUDA_AVAILABLE=1` preprocessor flag - Add `cuda_shim_slim_cpp_unittest()` function for SlimTensor test targets Differential Revision: [D90126244](https://our.internmc.facebook.com/intern/diff/D90126244/)

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

…sor conversion Pull Request resolved: #16551 Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads ghstack-source-id: 336360657 @exported-using-ghexport Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/)

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

…sor conversion Pull Request resolved: #16551 Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads ghstack-source-id: 336512812 @exported-using-ghexport Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/)

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

…sor conversion Pull Request resolved: #16551 Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads ghstack-source-id: 336530258 @exported-using-ghexport Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/)

… to SlimTensor conversion" Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/) [ghstack-poisoned]

…sor conversion Pull Request resolved: #16551 Add from_etensor() factory function that creates a SlimTensor from an ExecuTorch portable tensor (ETensor), copying data to a target device. Key features: - Handles int32_t to int64_t conversion for sizes/strides (ETensor uses int32_t, SlimTensor uses int64_t) - Supports CPU and CUDA target devices via storage()->copy_() - Preserves tensor strides (non-contiguous layouts) - Provides both reference and pointer overloads ghstack-source-id: 336538672 @exported-using-ghexport Differential Revision: [D90539554](https://our.internmc.facebook.com/intern/diff/D90539554/)

Gasoonjia mentioned this pull request Jan 6, 2026

[slimtensor] Add CUDA slimtensor creation with basic functionality #16439

Merged

meta-cla bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jan 12, 2026

meta-codesync bot added fb-exported meta-exported labels Jan 12, 2026

Gasoonjia mentioned this pull request Jan 13, 2026

[slimtensor] integration into backend #16565

Open

Gasoonjia added 3 commits January 13, 2026 16:33

Gasoonjia mentioned this pull request Jan 21, 2026

[slimtensor] Introduce CUDA guard to aoti/slim/cuda #16724

Merged

Gasoonjia added 3 commits January 22, 2026 23:11

larryliu0820 approved these changes Jan 28, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[slimtensor] Add from_etensor factory function for ETensor to SlimTensor conversion #16551

[slimtensor] Add from_etensor factory function for ETensor to SlimTensor conversion #16551

Gasoonjia commented Jan 12, 2026 •

edited

Loading

Uh oh!

pytorch-bot bot commented Jan 12, 2026 •

edited

Loading

Uh oh!

github-actions bot commented Jan 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[slimtensor] Add from_etensor factory function for ETensor to SlimTensor conversion #16551

Are you sure you want to change the base?

[slimtensor] Add from_etensor factory function for ETensor to SlimTensor conversion #16551

Conversation

Gasoonjia commented Jan 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Jan 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16551

⏳ 42 Pending, 2 Unrelated Failures

Uh oh!

github-actions bot commented Jan 12, 2026

This PR needs a release notes: label

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Gasoonjia commented Jan 12, 2026 •

edited

Loading

pytorch-bot bot commented Jan 12, 2026 •

edited

Loading

This PR needs a `release notes:` label