CVE-2025-62426 MEDIUM

CVE-2025-62426: vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Vendor Vllm-Project
Product vllm
Weakness CWE-770 · Uncontrolled resource consumption
Published November 21, 2025
Last update November 24, 2025
View on NVD All CVEs

CVSS base score

6.5/10
Attack vector Network
Attack complexity Low
Privileges required Low
User interaction None
Confidentiality None
Integrity None

CVSS vector

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

What the vulnerability does

01Description

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.

Key dates

02Disclosure timeline

November 21, 2025 CVE published
November 24, 2025 Record updated