[Core] Support logprobs with spec decode + async scheduling (#29223)

Signed-off-by: Nick Hill <nhill@redhat.com>

vllm/v1/core/sched/scheduler.py

@@ -1089,8 +1089,6 @@ class Scheduler(SchedulerInterface):
                 and request.sampling_params.logprobs is not None
                 and logprobs
             ):
-                # NOTE: once we support N tokens per step (spec decode),
-                # the outer lists can be of length > 1.
                 new_logprobs = logprobs.slice(req_index, req_index + 1)
 
             if new_token_ids and self.structured_output_manager.should_advance(request):