CVE-2025-46570
Low
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.
SeverityLow
CVSS2.6
Exploit probability—
ProductVllm
PublishedMay 29, 2025
First seenMay 29, 2025
Weakness typeCWE-208CWE-208
How to fix
Update
- vllm vllm0.9.0 or later
- vllm0.9.0 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm vllm | v < 0.9.0 | 0.9.0 |
| vllmPyPI | v < 0.9.0 | 0.9.0 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.