/
DirectorySecurity AdvisoriesPricing
Sign In
Security Advisories

CVE-2025-46570

Published

Last updated

NVD

https://nvd.nist.gov/vuln/detail/CVE-2025-46570

Severity

Unknown

Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.

References

Affected packages


Safe Source for Open Sourceâ„¢
Media KitContact Us
© 2025 Chainguard. All Rights Reserved.
Private PolicyTerms of Use

Products

Chainguard ContainersChainguard LibrariesChainguard VMs