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…
Severity low: primary CNA CVSS 2.6 v3.1 (worst CNA-provided scenario) Not listed in this KEV snapshot. Forecast present in this snapshot.
Published 2025-05-29T16:32:42.794Z. Updated 2025-05-29T18:05:10.768Z.