VULNERABILITY INTELLIGENCE

CVE-2025-62426

CVSS score6.5 MEDIUM

EPSS probability0.54%

CISA KEVNot currently listed

Published2025-11-21

Last modified2026-10-19

CVSS vectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

Weakness classification

security-advisories@github.com: CWE-770

Primary references

security-advisories@github.com — Product
security-advisories@github.com — Product
security-advisories@github.com — Patch
security-advisories@github.com — Issue Tracking
security-advisories@github.com — Vendor Advisory