HIGH 8.2 NVD
CVE-2026-116178
vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal me
vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3m
- https://www.vulncheck.com/advisories/vllm-0.20.0-before-0.30.0-dos-via-inference-v1-genera
This high severity vulnerability with a CVSS score of 8.2 was published on 2026-10-25 via NVD.
vulnfeed aggregates 17091 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.