Skip to content

Arm backend: Fix bug of inserting unnecessary casts for aten.where.self #11816

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 3 commits into from
Jun 19, 2025
+8 −1
Merged

Arm backend: Fix bug of inserting unnecessary casts for aten.where.self #11816

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
918af66
Arm backend: Fix bug of inserting unnecessary casts for aten.where.self
YufengShi-dudu Jun 18, 2025
2bbc032
Merge branch 'main' into add-int32-support-to-where-op
YufengShi-dudu Jun 19, 2025
b042484
Merge branch 'main' into add-int32-support-to-where-op
YufengShi-dudu Jun 19, 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
2 changes: 1 addition & 1 deletion backends/arm/_passes/match_where_self_arg_dtype_pass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ def call(self, graph_module: torch.fx.GraphModule):

input_dtype = input_.meta["val"].dtype
other_dtype = other_.meta["val"].dtype
target_dtype = torch.float32
target_dtype = input_dtype
if input_dtype != other_dtype:
target_dtype = get_largest_dtype(input_dtype, other_dtype)

Expand Down
7 changes: 7 additions & 0 deletions backends/arm/test/ops/test_where.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,6 +121,12 @@ def scalar_condition(input: torch.Tensor):
scalar_condition,
)

int32_scalar_cond = Where(
1,
torch.int32,
scalar_condition,
)

test_modules_common = {
"two_dim_tensor_cond": lambda: two_dim_tensor_cond,
"three_dim_tensor_cond": lambda: three_dim_tensor_cond,
Expand All @@ -134,6 +140,7 @@ def scalar_condition(input: torch.Tensor):
**test_modules_common,
"float32_tensor_cond_tuple_dtype": lambda: float32_tensor_cond_tuple_dtype,
"float32_tensor_cond_tuple_dtype_bool": lambda: float32_tensor_cond_tuple_dtype_bool,
"int32_scalar_cond": lambda: int32_scalar_cond,
}

test_modules_BI = {
Expand Down
Loading