Skip to content

Ensure the correct output data type for the full op. #13349

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 1 commit into from
Aug 14, 2025
Merged

Ensure the correct output data type for the full op. #13349

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: 7 additions & 1 deletion backends/cadence/aot/replace_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2327,10 +2327,16 @@ def call(self, graph_module: torch.fx.GraphModule) -> PassResult:
# Cast the const_arg to the dtype of the x_arg
full_arg = self.resolve_full_arg(x_arg, const_arg)

full_output_dtype = (
torch.int32 if isinstance(full_arg, int) else torch.float32
)

# Extract an argument to a separate full op.
with graph_module.graph.inserting_before(mul_node):
full_node = graph_module.graph.call_function(
torch.ops.aten.full.default, args=([1], full_arg)
torch.ops.aten.full.default,
args=([1], full_arg),
kwargs={"dtype": full_output_dtype},
)
full_node.meta = mul_node.meta
full_node.meta["val"] = [1]
Expand Down
Loading