diff --git a/vllm/v1/engine/detokenizer.py b/vllm/v1/engine/detokenizer.py
index 0ccbe65493499..38f435f5166e0 100644
--- a/vllm/v1/engine/detokenizer.py
+++ b/vllm/v1/engine/detokenizer.py
@@ -233,6 +233,11 @@ class FastIncrementalDetokenizer(BaseIncrementalDetokenizer):
     def _protected_step(self, next_token_id: int) -> Optional[str]:
         try:
             token = self.stream.step(self.tokenizer, next_token_id)
+        except OverflowError:
+            # Handle rare observed overflow, still to be diagnosed.
+            # See https://github.com/vllm-project/vllm/issues/21951.
+            logger.exception("Encountered invalid token id: %d", next_token_id)
+            token = None
         except Exception as e:
             if not str(e).startswith(INVALID_PREFIX_ERR_MSG):
                 raise e