CVE-2026-116178vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders
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.
Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.
Affected products and versions
| Vendor | Product | Versions | |
|---|---|---|---|
| vllm-project | vllm | 0.20.0 – < 0.30.0, fixed 0.30.0 |
References and patches
- GitHub Security Advisory (GHSA-34qw-q2h2-jp3m) vendor-advisoryPatchVendor Advisory
- VulnCheck Advisory: vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders third-party-advisoryThird Party Advisory
CPE matches (NVD) (1)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.20.0 < 0.30.0