All vulnerabilities
CVE-2026-116178GHSA-34qw-q2h2-jp3m

vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders

vllm-project vllm
CVSS
8.2High
ExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)No scoreNo FIRST EPSS score in this snapshot yet
Fixed in0.30.0Fixed versionCVE List
Published25 Oct 2026Updated 25 Oct 2026CVE List

What fixes it

A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.

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.

Text from CVE List

Affected versions 2

  • vllmaffected: 0.20.0 before 0.30.0CVE List
  • vllmunaffected: 0.30.0CVE List

References 2