diff --git a/sam3/perflib/fused.py b/sam3/perflib/fused.py
index 6800cca64..4f7455657 100644
--- a/sam3/perflib/fused.py
+++ b/sam3/perflib/fused.py
@@ -9,7 +9,14 @@
 
 def addmm_act(activation, linear, mat1):
     if torch.is_grad_enabled():
-        raise ValueError("Expected grad to be disabled.")
+        # Training path: the fused kernel below is inference-only (detached
+        # weights, bf16 cast), so fall back to standard autograd-friendly ops.
+        y = linear(mat1)
+        if activation in [torch.nn.functional.relu, torch.nn.ReLU]:
+            return torch.nn.functional.relu(y)
+        if activation in [torch.nn.functional.gelu, torch.nn.GELU]:
+            return torch.nn.functional.gelu(y)
+        raise ValueError(f"Unexpected activation {activation}")
     self = linear.bias.detach()
     mat2 = linear.weight.detach()
     self = self.to(torch.bfloat16)