diff --git a/segment_anything/modeling/image_encoder.py b/segment_anything/modeling/image_encoder.py
index da9141c..dcee6cd 100644
--- a/segment_anything/modeling/image_encoder.py
+++ b/segment_anything/modeling/image_encoder.py
@@ -315,8 +315,8 @@ def get_rel_pos(q_size: int, k_size: int, rel_pos: torch.Tensor) -> torch.Tensor
         rel_pos_resized = rel_pos
 
     # Scale the coords with short length if shapes for q and k are different.
-    q_coords = (torch.arange(q_size).to(rel_pos.device)[:, None] * max(k_size / q_size, 1.0))
-    k_coords = (torch.arange(k_size).to(rel_pos.device)[None, :] * max(q_size / k_size, 1.0))
+    q_coords = (torch.arange(q_size, device=rel_pos.device)[:, None] * max(k_size / q_size, 1.0))
+    k_coords = (torch.arange(k_size, device=rel_pos.device)[None, :] * max(q_size / k_size, 1.0))
     relative_coords = (q_coords - k_coords) + (k_size - 1) * max(q_size / k_size, 1.0)
 
     return rel_pos_resized[relative_coords.long()]