Skip to content

aoti_torch_copy_ #14689

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

Merged
merged 5 commits into from
Sep 30, 2025
Merged

aoti_torch_copy_ #14689

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
49602cd
tensor destroy
larryliu0820 Sep 30, 2025
975fb6b
aoti_torch_create_tensor_from_blob_v2
larryliu0820 Sep 30, 2025
167e603
aoti_torch__reinterpret_tensor
larryliu0820 Sep 30, 2025
8002927
aoti_torch_copy_
larryliu0820 Sep 30, 2025
c4ba555
Merge branch 'main' into gh/larryliu0820/79/head
larryliu0820 Sep 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions backends/aoti/utils.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,23 @@ inline AOTITorchError validate_storage_offset(int64_t storage_offset) {
return Error::Ok;
}

// Check if tensor is in contiguous memory format (NCHW for 4D tensors)
// Contiguous format means strides decrease from left to right:
// For NCHW: strides = [C*H*W, H*W, W, 1]
inline bool is_tensor_contiguous(
int64_t ndim,
const int64_t* sizes,
const int64_t* strides) {
int64_t expected_stride = 1;
for (int64_t i = ndim - 1; i >= 0; i--) {
if (strides[i] != expected_stride) {
return false;
}
expected_stride *= sizes[i];
}
return true;
}

} // extern "C"

} // namespace aoti
Expand Down
Loading
Loading