ray.serve.request_router.RequestRouter.backoff_sequence_s#

RequestRouter.backoff_sequence_s = [0, 0.05, 0.1, 0.15, 0.2, 0.5, 1.0]#

The sequence of backoff timeouts to use when all replicas’ queues are full. The last item in the list is the max timeout and will be used repeatedly.