CVE-2025-46570 Details

A timing-based side-channel vulnerability has been identified in vLLM, an inference engine for large language models, prior to version 0.9.0. The issue arises from the prefix caching mechanism, which can be exploited to infer prompt reuse through timing differences. When a prompt is processed, matching prefix chunks accelerate the prefill process, creating noticeable timing variations. This vulnerability could be exploited to guess sensitive inputs by measuring response times, potentially leading to the leakage of private information.

Users can update to vLLM version 0.9.0 or later, where this vulnerability has been patched.