diff --git a/vllm/distributed/kv_transfer/kv_connector/v1/hf3fs/utils/gather_scatter_helper.py b/vllm/distributed/kv_transfer/kv_connector/v1/hf3fs/utils/gather_scatter_helper.py
index aebaecd40b..4ba3ecee90 100644
--- a/vllm/distributed/kv_transfer/kv_connector/v1/hf3fs/utils/gather_scatter_helper.py
+++ b/vllm/distributed/kv_transfer/kv_connector/v1/hf3fs/utils/gather_scatter_helper.py
@@ -4,6 +4,7 @@ import torch
 
 from vllm.logger import init_logger
 from vllm.triton_utils import tl, triton
+from vllm.utils.torch_utils import async_tensor_h2d
 
 
 @triton.jit
@@ -140,9 +141,9 @@ def scatter_kv_caches(
     assert len(kv_cache_strides) == 4
 
     device = src_tensor.device
-    token_indices_tensor = torch.tensor(
-        token_indices, dtype=torch.int32, device="cpu"
-    ).to(device, non_blocking=True)
+    token_indices_tensor = async_tensor_h2d(
+        token_indices, device=device, dtype=torch.int32
+    )
 
     grid = (num_layers, num_tokens_in_block)
     BLOCK_SIZE = 128
@@ -196,9 +197,9 @@ def gather_kv_caches(
     assert len(kv_cache_strides) == 4
 
     device = dst_tensor.device
-    token_indices_tensor = torch.tensor(
-        token_indices, dtype=torch.int32, device="cpu"
-    ).to(device, non_blocking=True)
+    token_indices_tensor = async_tensor_h2d(
+        token_indices, device=device, dtype=torch.int32
+    )
 
     grid = (num_layers, num_tokens_in_block)
     BLOCK_SIZE = 128