diff --git a/vllm_ascend/spec_decode/mtp_proposer.py b/vllm_ascend/spec_decode/mtp_proposer.py
index 8cb46fa2..a152aa47 100644
--- a/vllm_ascend/spec_decode/mtp_proposer.py
+++ b/vllm_ascend/spec_decode/mtp_proposer.py
@@ -725,7 +725,6 @@ class MtpProposer(Proposer):
         has_lora = len(self.runner.input_batch.lora_id_to_lora_request) > 0
         aclgraph_runtime_mode, batch_descriptor = \
             self.runner.cudagraph_dispatcher.dispatch(num_tokens=num_input_tokens, uniform_decode=uniform_decode, has_lora=has_lora)
-        original_aclgraph_runtime_mode = aclgraph_runtime_mode
         if self.use_async_scheduling:
             # there is synchronization between mtp steps when enabling aclgraph,
             # disable aclgraph when use async scheduling to avoid the
@@ -779,8 +778,8 @@ class MtpProposer(Proposer):
                         hidden_states = torch.ops.vllm.maybe_pad_and_reduce(
                             hidden_states)
 
-                    if original_aclgraph_runtime_mode == CUDAGraphMode.FULL and \
-                        self.use_async_scheduling and attn_metadata[layer_name].decode is not None:
+                    if self.use_async_scheduling and attn_metadata[
+                            layer_name].decode is not None:
                         for layer_name in self.attn_layer_name:
                             actual_size = len(attn_metadata[layer_name].decode.
                                               actual_seq_lengths_q)