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 5, 16:00 UTC
[BugFix] Fix precommit breakage due to conflicting in-flight merges (#38759)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Nick Hill committed
Apr 1, 2026 at 15:35 UTC
6241521dd2751b036d43d4bfc965f68319c32068
1 file changed
+1
-1
vllm/v1/executor/ray_executor_v2.py
+1
-1
@@ -420,7 +420,7 @@ class RayExecutorV2(MultiprocExecutor):
420
for response_mq in self.response_mqs:
421
response_mq.wait_until_ready()
422
423
- self.futures_queue = deque[tuple[FutureWrapper, Any]]()
423
+ self.futures_queue = deque[FutureWrapper]()
424
self._post_init_executor()
425
426
self.start_worker_monitor()