CVE-2026-94624

[CVE catalog]

Severity

High · CVSS 8.7CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Published

Sep 21, 2026, 10:00:00 PM UTC

Updated

Sep 21, 2026, 10:17:01 PM UTC

Source

[NVD] · [CVE record]

EPSS

0.63% · Oct 25, 2026

A flaw was found in vLLM. A remote attacker can exploit a denial of service vulnerability in the P2P KV offloading mechanism. By supplying arbitrary remote host and port values, an attacker can create unreachable peer sessions that consume ZeroMQ sockets. This resource exhaustion leads to an uncaught error, crashing the EngineCore and stopping all inference, thereby causing a denial of service. vllm: vLLM: Denial of Service via unbounded P2P KV offloading sessions Important: A denial of service vulnerability exists in vLLM's P2P KV offloading, affecting Red Hat AI Inference Server and Red Hat OpenShift AI. This flaw allows an unauthenticated attacker to exhaust ZeroMQ sockets by supplying arbitrary remote host and port values, leading to a crash of the EngineCore and disruption of inference services. This is particularly relevant when vLLM is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.