Skip to content

ENH: fix is_jax_array under torch.compile #464

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
lucascolley wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −0
Open

ENH: fix is_jax_array under torch.compile #464

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
7 changes: 7 additions & 0 deletions src/array_api_compat/common/_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,13 @@ def _is_jax_zero_gradient_array(x: object) -> TypeGuard[_ZeroGradientArray]:
dtype = x.dtype # type: ignore[attr-defined]
except AttributeError:
return False

torch = sys.modules.get("torch")
if torch is not None and torch.compiler.is_compiling():
# Under torch.compile tracing, `type(dtype)` can't be modeled by Dynamo
# for objects it hasn't fully specialized (e.g. attrs on empty tuples).
return False

cls = cast(Hashable, type(dtype))
if not _issubclass_fast(cls, "numpy.dtypes", "VoidDType"):
return False
Expand Down
Loading