Vulnerability in vllm-project vllm

[ Description ]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.

[ Fixes ]Fixes and patches

• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Advisories ]Government CERT advisories

• BSI CERT-Bund25 Oct 2026WID-SEC-2026-4151

  vllm: Multiple vulnerabilities allow denial of service Translated from German

  CVE-2026-116175CVE-2026-116174CVE-2026-116181

[ References ]References

• github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvprPatchVendor Advisory
• www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-write-…Third Party Advisory