From 6accb21f2a9aa2411a2eb23f96ac90828554f3f4 Mon Sep 17 00:00:00 2001 From: Aaron Hao Date: Wed, 18 Mar 2026 18:49:02 -0700 Subject: [PATCH] [bug] Fix deadlock with pause resume and collective_rpc (#37024) Signed-off-by: hao-aaron --- vllm/v1/engine/core.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/vllm/v1/engine/core.py b/vllm/v1/engine/core.py index 7d962f740..421b25c0d 100644 --- a/vllm/v1/engine/core.py +++ b/vllm/v1/engine/core.py @@ -1632,7 +1632,11 @@ class DPEngineCoreProc(EngineCoreProc): if self.has_coordinator and request_wave != self.current_wave: if request_wave > self.current_wave: self.current_wave = request_wave - elif not self.engines_running: + elif ( + not self.engines_running + and self.scheduler.pause_state == PauseState.UNPAUSED + ): + self.engines_running = True # Request received for an already-completed wave, notify # front-end that we need to start the next one. self.output_queue.put_nowait(