Skip to content

Arm backend: Stabilize MobileNetV3 fp16 TOSA test #19590

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
bdemirb wants to merge 2 commits into
base: main
Choose a base branch
from
+5 −2
Open

Arm backend: Stabilize MobileNetV3 fp16 TOSA test #19590

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0dfb987
Arm backend: Stabilize MobileNetV3 fp16 TOSA test
May 13, 2026
8b6ff2e
Merge branch 'main' into fix-mv3-fp16-flaky-tolerance
bdemirb May 15, 2026
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: 5 additions & 2 deletions backends/arm/test/models/test_mobilenet_v3_arm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,14 +47,17 @@ def test_mv3_tosa_FP():

@pytest.mark.slow
def test_mv3_tosa_FP_fp16():
inputs_fp16 = tuple(t.to(torch.float16) for t in model_inputs)
input_tensor_fp16 = torch.rand(
1, 3, 232, 232, generator=torch.Generator().manual_seed(0)
)
inputs_fp16 = (normalize(input_tensor_fp16).to(torch.float16),)
pipeline = TosaPipelineFP[input_t](
mv3_fp16,
inputs_fp16,
aten_op=[],
exir_op=[],
use_to_edge_transform_and_lower=True,
atol=5e-2,
atol=6e-2,
)
pipeline.run()

Expand Down
Loading