Vulnerability · Published Oct 25, 2026 · Assigned by VulnCheck

CVE-2026-116178vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders

Medium 5.9

In plain English

A medium-severity improper input validation in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 26% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)5.9Medium

Exploit odds (30 days)0.3%top 73.6% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.30.0	PYSEC-2026-4353

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0.20.0 – before 0.30.0

Weakness: CWE-20 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

References

GitHub Security Advisory (GHSA-34qw-q2h2-jp3m) vendor-advisory
VulnCheck Advisory: vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders third-party-advisory