vllm p2p never connected zmq_exhaustion

影響: pip:vllm < 0.32.0 → 0.32.0

When the OffloadingConnector uses TieringOffloadingSpec with a P2P secondary tier, an API client can submit many unique non-listening peer addresses through kv_transfer_params.prefill. vLLM keeps every never-established P2P session and its ZeroMQ sockets after the request finishes. On vLLM 0.26.0, 340 such peers filled the default ZeroMQ context socket quota; creating the next peer raised an uncaught ZMQError, terminated EngineCore, and shut down the API server. The path was reproduced with a n…

在 GitHub Advisory Database 阅读

2026/10/27 23:45，GitHub Advisory Database 发布了“vllm p2p never connected zmq_exhaustion”（类型：漏洞公告）。严重程度为“中危”（medium）。相关技术：Python。CVE：CVE-2026-94624。