CVE-2025-46570 — 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…
Published: 2025-05-29 · CVSS: 2.6 · CVSS 3.1
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7