Skip to content

[slimtensor] Add aoti_torch_copy_ for SlimTensor #16451

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
Gasoonjia wants to merge 13 commits into
base: gh/gasoonjia/93/base
Choose a base branch
from
Open

[slimtensor] Add aoti_torch_copy_ for SlimTensor #16451

Gasoonjia wants to merge 13 commits into from
+523 −0

Conversation

@Gasoonjia
Copy link
Contributor

@Gasoonjia Gasoonjia commented Jan 5, 2026 •
edited
Loading

Stack from ghstack (oldest at bottom):

Add SlimTensor-based aoti_torch_copy_() - Copies data from source tensor to destination tensor. Delegates to SlimTensor's copy_() which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: D90126246

@Gasoonjia
[slimtensor] Add aoti_torch_copy_ for SlimTensor
1e2ee90 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@pytorch-bot
Copy link

pytorch-bot bot commented Jan 5, 2026 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16451

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

⏳ No Failures, 109 Pending

As of commit 2557152 with merge base c487340 (image):
💚 Looks good so far! There are no failures yet. 💚

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

This was referenced Jan 5, 2026
Merged
Merged
Merged
Merged
Merged
@github-actions
Copy link

github-actions bot commented Jan 5, 2026

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.

This was referenced Dec 27, 2025
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Merged
Open
Open
Open
Open
Open
Open
@meta-cla 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 5, 2026
This was referenced Jan 6, 2026
Open
Open
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
0cbd14f 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia Gasoonjia mentioned this pull request Jan 13, 2026
Open
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
08fe5e1 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
7d26c5e 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
c80c6a9 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia Gasoonjia mentioned this pull request Jan 21, 2026
Merged
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
622a40a 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
a229b35 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
This was referenced Jan 22, 2026
Merged
Merged
Merged
Merged
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
972795a 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
30c909b 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
5c94707 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Jan 27, 2026
@Gasoonjia
[slimtensor] Introduce CUDA guard to aoti/slim/cuda (#16724)
4af7c3e 
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/)
Gasoonjia added a commit that referenced this pull request Jan 27, 2026
@Gasoonjia
[slimtensor] Add SlimTensor-based aoti_torch_create_tensor_from_blob_…
665facc 
…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/)
Gasoonjia added a commit that referenced this pull request Jan 27, 2026
@Gasoonjia
[slimtensor] Add SlimTensor-based aoti_torch_empty_strided (#16447)
c653d80 
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/)
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
59a5a31 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Jan 28, 2026
@Gasoonjia
[slimtensor] Add aoti_torch_copy_ for SlimTensor
e401c2b 
Pull Request resolved: #16451

Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).
ghstack-source-id: 336294938
@exported-using-ghexport

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
da3edb1 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
Gasoonjia added a commit that referenced this pull request Jan 28, 2026
@Gasoonjia
[slimtensor] Add aoti_torch_copy_ for SlimTensor
e9c2131 
Pull Request resolved: #16451

Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).
ghstack-source-id: 336304836
@exported-using-ghexport

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)
Gasoonjia added a commit that referenced this pull request Jan 28, 2026
@Gasoonjia
[slimtensor] Add aoti_torch_delete_tensor_object for SlimTensor (#16448)
e875474 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #16451
* #16450
* #16449
* __->__ #16448

Add `aoti_torch_delete_tensor_object()` - Deletes a tensor object.
SlimTensor uses SharedPtr-based reference counting, so simply deleting
the tensor automatically handles storage deallocation when the last
reference is removed.

Differential Revision:
[D90126248](https://our.internmc.facebook.com/intern/diff/D90126248/)
Gasoonjia added a commit that referenced this pull request Jan 28, 2026
@Gasoonjia
[slimtensor] Add aoti_torch_new_tensor_handle for SlimTensor (#16449)
b5428fa 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #16451
* #16450
* __->__ #16449
* #16448

Add `aoti_torch_new_tensor_handle()` - Creates a new tensor handle that
shares storage with the original tensor. Uses SlimTensor's copy
constructor which shares the SharedPtr<Storage>, so both tensors
reference the same memory.

Differential Revision:
[D90126245](https://our.internmc.facebook.com/intern/diff/D90126245/)
@Gasoonjia
Update on "[slimtensor] Add aoti_torch_copy_ for SlimTensor"
2557152 
Add SlimTensor-based `aoti_torch_copy_()` - Copies data from source tensor to destination tensor. Delegates to SlimTensor's `copy_()` which handles all device combinations (CPU-CPU, CPU-CUDA, CUDA-CPU, CUDA-CUDA).

Differential Revision: [D90126246](https://our.internmc.facebook.com/intern/diff/D90126246/)

[ghstack-poisoned]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@larryliu0820 larryliu0820 larryliu0820 approved these changes

Assignees

No one assigned

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

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@Gasoonjia @larryliu0820