CVE-2025-46570
vLLM is an inference and serving engine for large language models (LLMs).
Does this matter?
Lower severity and a low EPSS score (0.43%). Track it; it rarely justifies an emergency change on its own.
Description
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.
- CVSS 3.1
- 2.6 LOWCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N
- EPSS
- 0.43% probability · 37th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-208, CWE-203
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
EPSS 0.4% since 26 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.