CVE-2025-46570
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
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.
Reserved 2025-04-24 | Published 2025-05-29 | Updated 2025-05-29 | Assigner GitHub_MCWE-208: Observable Timing Discrepancy
github.com/...t/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
github.com/vllm-project/vllm/pull/17045
github.com/...ommit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
Support options
