CVSS 3.1
2.6 lowCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:NCVE-2025-46570
Low (2.6) in vllm vllm. EPSS 0.4% chance of exploitation in the next 30 days. Fixed in vllm 0.9.0.
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.
Severity
- EPSS
- 0.4% chance of exploitation in the next 30 days; higher than 37% of CVEs (scores of 2026-10-31)
- CWEs
- CWE-203, CWE-208
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-4qjh-9fv9-r85r | PyPI | vllm | <0.9.0 | 0.9.0 |
| PYSEC-2025-53 | PyPI | vllm | <0.9.0 | 0.9.0 |