CVE-2026-116178

Summary

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.

Impact & exploitability

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected products we track (1)

Recommendation

Apply the vendor fix in your normal patch cycle. Open any affected product above for its exact safe version.

Official patch: https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3m ↗

Additional information

• NVD record
• https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3mPatch
• https://www.vulncheck.com/advisories/vllm-0.20.0-before-0.30.0-dos-via-inference-v1-generate-mm-placeholdersAdvisory