vLLM P2P offloading session resource exhaustion vulnerability can cause service crash, fixed in 0.32.0
vllm p2p never connected zmq_exhaustion
vLLM released a security advisory (CVE-2026-94624), disclosing a resource exhaustion vulnerability when OffloadingConnector is used with TieringOffloadingSpec to enable the P2P secondary tier; versions before 0.32.0 are affected, and it has been fixed in 0.32.0. An attacker only needs access to the OpenAI-compatible inference endpoint and an ordinary API key; by submitting a large number of unique non-listening peer addresses via kv_transfer_params.prefill, vLLM retains each never-established P2P session and its ZeroMQ socket without cleanup. In a test with vLLM 0.26.0's default MAX_SOCKETS=1023, 340 peers occupy approximately 1020 sockets, and the next peer triggers an uncaught ZMQError, terminating EngineCore and causing the API service to exit; approximately 341 requests are enough to stop an instance from performing inference until restart.
The advisory provides the trigger conditions and the quantified boundary that approximately 341 requests can take down the service; teams deploying vLLM P2P offloading can use this to check their version and upgrade to 0.32.0.