[Redo] #26368 (#28771)

Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

vllm/v1/core/sched/scheduler.py

@@ -1010,8 +1010,8 @@ class Scheduler(SchedulerInterface):
                 continue
 
             req_index = model_runner_output.req_id_to_index[req_id]
-            generated_token_ids = (
-                sampled_token_ids[req_index] if sampled_token_ids else []
+            generated_token_ids: list[int] = (
+                sampled_token_ids[req_index].tolist() if sampled_token_ids else []
             )
 
             scheduled_spec_token_ids = (