CVE-2025-62426: 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 ...

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.

Metrics

CVSS 3.1

6.5/10

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

EPSS Probability

0.32%

23.6th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-770

Affected Software

Vendor	Product	Versions	Update
Vllm	Vllm	>= 0.5.5, < 0.11.1	—
Vllm	Vllm	0.11.1	Rc0

References

Timeline

Published: Nov 21, 2025
Last Modified: Jun 17, 2026
Status: Analyzed

Frequently Asked Questions

What is CVE-2025-62426?

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.

How severe is CVE-2025-62426?

CVE-2025-62426 has a CVSS score of 6.5/10 (MEDIUM severity). The EPSS model estimates a 0.32% probability of exploitation in the next 30 days.

How do I fix CVE-2025-62426?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.