CVE-2025-46570

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.

The following products are affected by CVE-2025-46570 vulnerability.

Here, you will find a curated list of external links that provide in-depth information to CVE-2025-46570.

URL	Resource
https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
https://github.com/vllm-project/vllm/pull/17045
https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
https://nvd.nist.gov/vuln/detail/CVE-2025-46570
https://www.cve.org/CVERecord?id=CVE-2025-46570