diff --git a/vllm_ascend/spec_decode/eagle_proposer.py b/vllm_ascend/spec_decode/eagle_proposer.py
index aa86823f..00c26e30 100644
--- a/vllm_ascend/spec_decode/eagle_proposer.py
+++ b/vllm_ascend/spec_decode/eagle_proposer.py
@@ -559,6 +559,8 @@ class SpecDecodeBaseProposer(EagleProposer):
                 common_attn_metadata.num_reqs = num_reqs_padded
                 common_attn_metadata.query_start_loc = self.runner.query_start_loc.gpu[: num_reqs_padded + 1]
                 common_attn_metadata.query_start_loc_cpu = self.runner.query_start_loc.cpu[: num_reqs_padded + 1]
+                common_attn_metadata.seq_lens = self.runner.seq_lens.gpu[:num_reqs_padded]
+                common_attn_metadata.seq_lens_cpu = self.runner.seq_lens.cpu[:num_reqs_padded]
         else:
             num_input_tokens = num_tokens
 
diff --git a/vllm_ascend/worker/model_runner_v1.py b/vllm_ascend/worker/model_runner_v1.py
index 859cef73..fc02fc0a 100644
--- a/vllm_ascend/worker/model_runner_v1.py
+++ b/vllm_ascend/worker/model_runner_v1.py
@@ -758,11 +758,11 @@ class NPUModelRunner(GPUModelRunner):
             self.gdn_query_start_loc.copy_to_gpu()
 
         self.seq_lens.np[:num_reqs] = self.input_batch.num_computed_tokens_cpu[:num_reqs] + num_scheduled_tokens
+        self.seq_lens.cpu[num_reqs:].fill_(0)
         self.seq_lens.copy_to_gpu()
 
         # Fill unused with -1. Needed for reshape_and_cache in attention_cp
         self.query_start_loc.gpu[num_reqs + 1 :].fill_(-1)
-        self.seq_lens.gpu[num_reqs:].fill_(0)
 
         # Copy the tensors to the NPU.
         self._prepare_input_ids(scheduler_output, total_num_scheduled_tokens, cu_num_tokens)