diff --git a/vllm/engine/llm_engine.py b/vllm/engine/llm_engine.py
index e3cd822f648..98c0e9eec27 100644
--- a/vllm/engine/llm_engine.py
+++ b/vllm/engine/llm_engine.py
@@ -1260,7 +1260,6 @@ def _advance_to_next_step(
                 assert len(seq_group.seqs) == 1
                 seq = seq_group.seqs[0]
                 seq.append_token_id(sample.output_token, sample.logprobs)
-                seq_group.update_num_computed_tokens(1)
 
     def step(self) -> List[Union[RequestOutput, EmbeddingRequestOutput]]:
         """Performs one decoding iteration and returns newly generated results.
diff --git a/vllm/engine/output_processor/multi_step.py b/vllm/engine/output_processor/multi_step.py
index 6dac3619580..e1aae841934 100644
--- a/vllm/engine/output_processor/multi_step.py
+++ b/vllm/engine/output_processor/multi_step.py
@@ -173,7 +173,6 @@ def _process_seq_outputs(self, seq: Sequence,
                 token_id=output_token_id,
                 logprobs=output_logprob,
             )
-            seq.data.update_num_computed_tokens(1)
 
             self._process_decode_and_stop(seq, sampling_params)