/
DirectorySecurity AdvisoriesPricing
Sign in
Security Advisories

CVE-2025-62426

Published

Last updated

NVD

https://nvd.nist.gov/vuln/detail/CVE-2025-62426

Severity

6.5

Medium

CVSS V3

Summary

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted chat_template_kwargs

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.

References

Affected packages


The trusted source for open source

Talk to an expert
© 2025 Chainguard. All Rights Reserved.
PrivacyTerms

Product

Chainguard ContainersChainguard LibrariesChainguard VMsIntegrationsPricing