CVE-2025-30165

vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a SUB ZeroMQ socket and connect to an XPUB socket on the primary vLLM host. When data ...

CVE-2025-30165

creationtimestamp| type| source ---|---|--- 2025-05-06 17:13:47+00:00| seen| https://infosec.exchange/users/cR0w/statuses/114462007419812570 2025-05-06 18:21:38+00:00| published-proof-of-concept| https://t.me/DarkWebInformerCVEAlerts/15182 2025-05-06 18:21:52+00:00| seen|...

CVE-2025-30165 Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a SUB ZeroMQ socket and connect to an XPUB socket on the primary vLLM host. When data ...