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.
Advisories
Source ID Title
Github GHSA Github GHSA GHSA-69j4-grxj-j64p vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Fri, 21 Nov 2025 01:45:00 +0000

Type Values Removed Values Added
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.
Title vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
Weaknesses CWE-770
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2025-11-21T01:21:29.546Z

Reserved: 2025-10-13T16:26:12.180Z

Link: CVE-2025-62426

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2025-11-21T02:15:43.570

Modified: 2025-11-21T02:15:43.570

Link: CVE-2025-62426

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.