CVE-2025-46570
Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
2.6
LOW
CVSS 3.1
EPSS 0.18%
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.
How to fix CVE-2025-46570
To remediate CVE-2025-46570, upgrade the affected package to a fixed version below.
- —upgrade to 0.9.0 or later
- —upgrade to 77073c77bc2006eb80ea6d5128f076f5e6c6f54f or later
Is CVE-2025-46570 being exploited?
Low — EPSS is 0.2%, meaning exploitation activity has not been observed at scale.
Affected packages (2)
- from 0, < 0.9.0
- from 0, < 77073c77bc2006eb80ea6d5128f076f5e6c6f54f | from 0, < 0.9.0
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | LOW2.6 | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N |