CVE-2026-116181: vllm vllm

CVSS 7.1 (high) · published 2026-10-25

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.

Affected products (NVD): vllm vllm

Fixed in (NVD): 0.29.0

Weakness: CWE-129

Source: NVD CVE-2026-116181

References

Check your software

Connect an AI agent to the FixLane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.