HomeVllmCVE-2025-62372

CVE-2025-62372

HIGH
8.3CVSS
Published: 2025-11-21
Updated: 2025-12-04
AI Analysis

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

CVSS Metrics

Vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Attack Vector
network
Complexity
low
Privileges
low
User Action
none
Confidentiality
undefined
Integrity
undefined
Availability
undefined
Weaknesses
CWE-129

Metadata

Primary Vendor
VLLM
Published
11/21/2025
Last Modified
12/4/2025
Source
NIST NVD
Note: Verify all details with official vendor sources before applying patches.

Affected Products

vllm : vllmvllm : vllmvllm : vllm

AI-Powered Remediation

Generate remediation guidance or a C-suite brief for this vulnerability.

Executive Intelligence Brief