Low severity · published May 29, 2025
CVE-2025-46570
vLLM is an inference and serving engine for large language models (LLMs)
2.6
CVSS
0.4%
EPSS
No
On KEV
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 vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N
Attack vector
Network
Complexity
High
Privileges
Low
User interaction
Required
Confidentiality
Low
Integrity
None
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 37% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
Vllm · Vllm
before 0.9.0 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-46570
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-46570
Patch
https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
Issue Tracking
https://github.com/vllm-project/vllm/pull/17045
Vendor Advisory
https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
More from Vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2025-47277
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache…