Skip to content

Fix AttributeError when torchao ops are not registered #18008

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
elpdumont wants to merge 1 commit into
base: main
Choose a base branch
from
+6 −2
Open

Fix AttributeError when torchao ops are not registered #18008

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
8 changes: 6 additions & 2 deletions exir/operator/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,9 @@ def gen_out_variant_schema(func_op_schema: str) -> str:
torch.ops.quantized_decomposed.choose_qparams.tensor,
]
try:
import torchao # noqa: F401
# Import quant_primitives directly to ensure custom ops are registered
# before accessing them via torch.ops.torchao
import torchao.quantization.quant_primitives # noqa: F401

_QUANT_PRIMITIVES.extend(
[
Expand All @@ -64,5 +66,7 @@ def gen_out_variant_schema(func_op_schema: str) -> str:
torch.ops.torchao.choose_qparams_affine.default,
]
)
except ImportError:
except (ImportError, AttributeError):
# ImportError: torchao or quant_primitives not installed
# AttributeError: torchao installed but operators not registered (e.g., older version)
pass
Loading