Vulnerability Description
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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.20.0, < 0.30.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3mPatchVendor Advisory
- https://www.vulncheck.com/advisories/vllm-0.20.0-before-0.30.0-dos-via-inferenceThird Party Advisory
FAQ
What is CVE-2026-116178?
CVE-2026-116178 is a vulnerability with a CVSS score of 5.9 (MEDIUM). 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/v...
How severe is CVE-2026-116178?
CVE-2026-116178 has been rated MEDIUM with a CVSS base score of 5.9/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-116178?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.