← Database

CVE-2026-116181

MEDIUM CVSS: 6.5 Published: 2026-10-25 Modified: 2026-10-25

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 Platforms

Unknown

Weakness Type

CWE-129

References