LLMMedium
CVE-2025-46570: vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, wh…
- Occurred
- May 29, 2025
- Published
- May 29, 2025
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2025-46570
- cvss:LOW
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: CVE describes a timing side-channel vulnerability in vLLM LLM serving engine, patched in version 0.9.0.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8