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…
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 metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mmplaceholders ranges or mismatched kwargsdata and mmhashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.
Part of the AI stack
This affects vLLM, in Inference & serving.
Assessment
- CVSS
- 8.2 (v4.0)
- Severity
- High
- Known exploited
- Not listed in CISA KEV
- Exploit availability
- Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
- Published
- 25 October 2026
- Last updated
- 28 October 2026
- Weakness
- CWE-20
- Assigner
- disclosure@vulncheck.com
CVSS vectorCVSS:4.0/AV:N/AC:H/AT:P/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
At the source
References
Query this programmatically
Agents can read this through the MCP endpoint, or over HTTP:
curl https://cve.zerocrew.in/api/cve/CVE-2026-116178