CVE-2026-116181 vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

What is CVE-2026-116181?

CVE-2026-116181 is a high-severity vulnerability in Vllm Vllm, published on 25 Oct 2026.

Official description

vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.

Weakness: CWE-129

Which versions are affected by CVE-2026-116181?

It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-116181?

No fix has been published for CVE-2026-116181 yet. Limit exposure of the affected software until one is available.

Is CVE-2026-116181 being exploited?

There is no known exploitation of CVE-2026-116181 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-f2x4-7hx3-gxfp, GHSA-w9r6-29q4-pvpr.