From a01a1c0d691f89fa4788102eb0bd9b15607c1cca Mon Sep 17 00:00:00 2001 From: Frelam Date: Sat, 10 Jan 2026 14:27:58 +0800 Subject: [PATCH] [Bugfix] fix encoder cache leak of waiting requests in scheduler to solve stuck in CPU scheduling (#31857) Signed-off-by: frelam Co-authored-by: Roger Wang --- vllm/v1/core/sched/scheduler.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/vllm/v1/core/sched/scheduler.py b/vllm/v1/core/sched/scheduler.py index a6bfa7a4a..462e2f47e 100644 --- a/vllm/v1/core/sched/scheduler.py +++ b/vllm/v1/core/sched/scheduler.py @@ -598,6 +598,11 @@ class Scheduler(SchedulerInterface): if new_blocks is None: # The request cannot be scheduled. + + # NOTE: we need to untouch the request from the encode cache + # manager + if request.has_encoder_inputs: + self.encoder_cache_manager.free(request) break # KVTransfer: the connector uses this info to determine