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

What is CVE-2026-116178?

CVE-2026-116178 is a high-severity vulnerability in Vllm Vllm, published on 25 Oct 2026.

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.

Weakness: CWE-20

Which versions are affected by CVE-2026-116178?

1 open source package ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-116178?

Upgrade vllm to 0.30.0 or later.

Is CVE-2026-116178 being exploited?

There is no known exploitation of CVE-2026-116178 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• GitHub advisory
• How this page is made

Also known as GHSA-34qw-q2h2-jp3m, GHSA-w9hx-wr9v-56wv, PYSEC-2026-4353.