icon

We found results for “

CVE-2025-46570

Good to know:

icon

Date: May 29, 2025

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.

Severity Score

Severity Score

Weakness Type (CWE)

Observable Timing Discrepancy

CWE-208

Top Fix

icon

Upgrade Version

Upgrade to version vllm - 0.9.0;https://github.com/vllm-project/vllm.git - v0.9.0

Learn More

CVSS v3.1

Base Score:
Attack Vector (AV): NETWORK
Attack Complexity (AC): HIGH
Privileges Required (PR): LOW
User Interaction (UI): REQUIRED
Scope (S): UNCHANGED
Confidentiality (C): LOW
Integrity (I): NONE
Availability (A): NONE

Do you need more information?

Contact Us