A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 21:15 UTC
[Misc][Core] Remove unused `req_index` increment in scheduler (#30176)
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Yifan Qiao committed
Dec 7, 2025 at 00:39 UTC
1b0482b9d1b8a082ff94a95516ec78349de6f515
1 file changed
-1
vllm/v1/core/sched/scheduler.py
-1
@@ -607,7 +607,6 @@ class Scheduler(SchedulerInterface):
607
608
self._update_connector_prefix_cache_stats(request)
609
610
- req_index += 1
610
self.running.append(request)
611
if self.log_stats:
612
request.record_event(