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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | 0.20.1 – < 0.29.0 | 0.29.0 |
Advisories 1
- WID-SEC-2026-4151 vllm: Mehrere Schwachstellen ermöglichen Denial of Service BSI CERT-Bund (WID) · Oct 25, 2026
References
- GitHub Security Advisory (GHSA-w9r6-29q4-pvpr) vendor-advisory
- VulnCheck Advisory: vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids third-party-advisory