aoti_torch_copy_ #14615
aoti_torch_copy_ #14615
Conversation
Gasoonjia
requested review from
kirklandsign and
larryliu0820
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14615
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 2 Unrelated FailuresAs of commit d961c1b with merge base df8d03b ( NEW FAILURE - The following job has failed:
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. |
meta-cla
bot
added
the
CLA Signed
|
@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating diff in D83094604. |
This PR needs a
|
Summary: This diff introduce `aoti_torch_copy_`, the function for copying tensor inside cuda backend. Right now it only support copy between tensors with same dtype. Reviewed By: larryliu0820 Differential Revision: D83094604
Gasoonjia
force-pushed
the
export-D83094604
branch
from
e684bb0 to
f410808
Compare
|
@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating diff in D83094604. |
Summary: this diff introduce aoti_tensor_empty_strided to et cuda backend, which will be one of the main functions to create empty tensor using the given stride. Reviewed By: larryliu0820 Differential Revision: D83094606
Summary: This diff introduce `aoti_torch_delete_tensor_object` for deleting tensors created during cuda backend inference. Reviewed By: larryliu0820 Differential Revision: D83094605
Summary: This function introduce aoti_torch_create_tensor_from_blob_v2, a function that create tensor from data blob and custom stride and size. Worth to notice that unlike aoti_torch_empty_strided, the tensor created by aoti_torch_create_tensor_from_blob_v2 will not have the control of the memory blob. Therefore when we delete it, the memory will not be freed. Reviewed By: larryliu0820 Differential Revision: D83094602
Summary: Introduced aoti_torch__reinterpret_tensor, which creates a new tensor view that reinterprets the same underlying memory with custom shape and strides. Reviewed By: larryliu0820 Differential Revision: D83094603
Summary: This diff introduce `aoti_torch_copy_`, the function for copying tensor inside cuda backend. Right now it only support copy between tensors with same dtype. Reviewed By: larryliu0820 Differential Revision: D83094604
Gasoonjia
force-pushed
the
export-D83094604
branch
from
f410808 to
1fc47cd
Compare
|
@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating diff in D83094604. |
Gasoonjia
force-pushed
the
export-D83094604
branch
from
1fc47cd to
d961c1b
Compare
|
@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating diff in D83094604. |
3 participants
Summary:
This diff introduce
aoti_torch_copy_, the function for copying tensor inside cuda backend.Right now it only support copy between tensors with same dtype.
Differential Revision: D83094604