Skip to content

Commit 9b3f660

Browse files
Arm backend: Xfail duplicate VGF input on Darwin (pytorch#22591)
MoltenVK rejects the incomplete descriptor layout generated by Model Converter for duplicated custom-shader inputs. Re-enable this test on Darwin once Model Converter preserves both descriptor bindings. cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani Signed-off-by: Sangwon Ha <sangwon.ha@arm.com>
1 parent 3574bf1 commit 9b3f660

1 file changed

Lines changed: 6 additions & 0 deletions

File tree

‎backends/arm/test/runtime/test_vgf_tensor_buffer_runtime.py‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@
66
import sys
77
from pathlib import Path
88

9+
import pytest
910
import torch
1011
import torch.nn.functional as F
1112

@@ -162,6 +163,11 @@ def test_two_input_add_buffer_shader_executes(tmp_path):
162163

163164
# Covers the two-input storage-buffer shader path when both inputs are the same tensor.
164165
# Checks runtime execution matches eager output for the duplicated-input add case.
166+
@pytest.mark.xfail(
167+
sys.platform == "darwin",
168+
reason="Model Converter drops duplicated custom-shader descriptor binding",
169+
strict=True,
170+
)
165171
@common.SkipIfNoModelConverter
166172
def test_two_input_add_buffer_shader_with_duplicated_input_executes(tmp_path):
167173
x = torch.randn(256)

0 commit comments

Comments
 (0)