diff --git a/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py b/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
index 93e20c3477bb..b838fd798bbc 100644
--- a/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
@@ -279,7 +279,7 @@ def rocm_aiter_grouped_topk(
     if e_score_correction_bias is not None:
         torch.ops.vllm.rocm_aiter_biased_grouped_topk(
             gating_output,
-            e_score_correction_bias,
+            e_score_correction_bias.to(gating_output.dtype),
             topk_weights,
             topk_ids,
             num_expert_group,
@@ -409,15 +409,15 @@ def shuffle_weights(
     *tensors: torch.Tensor, layout: tuple[int, int] = (16, 16)
 ) -> tuple[torch.Tensor, ...]:
     """
-    Applies shuffle_weight function from AITER to each 
+    Applies shuffle_weight function from AITER to each
     input tensor and returns them.
-    
+
     Rearranges (shuffles) the input tensor/s
     into a specified block layout for optimized computation.
 
     Args:
         *tensors: Variable number of torch.Tensor objects.
-        layout: A pair of integers specifying the 
+        layout: A pair of integers specifying the
         block sizes used to divide the tensors during shuffling.
         Default is (16, 16).