Skip to content

Remove named tensor handling from executorch (#19642) #19642

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

Open
jbschlosser wants to merge 1 commit into
base: main
Choose a base branch
from
+0 −4
Open

Remove named tensor handling from executorch (#19642) #19642

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 0 additions & 4 deletions codegen/api/et_cpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,6 @@
- Executorch doesn't support TensorOptions, however in this file we still keep the logic here to be compatible with
torchgen.api.cpp, so that we can do stuff like ATen mode (running ATen kernels in Executorch).

- Executorch doesn't support Dimname.

- Executorch runtime doesn't support SymInt, will treat it as int.
"""

Expand Down Expand Up @@ -141,8 +139,6 @@ def argumenttype_type(
# TODO: keeping these special cases for Tensor[] and Tensor?[] so that we can hookup with ATen kernels.
if str(t.elem) == "Tensor":
return NamedCType(binds, BaseCType(tensorListT))
elif str(t.elem) == "Dimname":
raise NotImplementedError("Executorch doesn't support Dimname")
elif str(t.elem) == "Tensor?":
return NamedCType(binds, ArrayRefCType(OptionalCType(BaseCType(tensorT))))
elem = argumenttype_type(t.elem, mutable=mutable, binds=binds)
Expand Down
Loading