Skip to content

Commit d73fbd8

Browse files
committed
fixing exp test
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
1 parent c20bd25 commit d73fbd8

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

torchao/experimental/tests/test_int8_dynamic_activation_intx_weight.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -647,9 +647,9 @@ def test_moe_quant_intx(self):
647647

648648
with torch.device("cpu"):
649649
model = MOEFeedForwardAOQuantizable(512, 256, 8, 2, empty_init=False).to(
650-
torch.bfloat16
650+
torch.float32
651651
)
652-
x = torch.randn(8, 512, dtype=torch.bfloat16)
652+
x = torch.randn(8, 512, dtype=torch.float32)
653653

654654
out = model(x).clone()
655655

0 commit comments

Comments
 (0)