CVE-2025-46570 Information

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.

Reference

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