VULNERABILITY INTELLIGENCE

CVE-2025-62372

CVSS score8.3 HIGH

EPSS probability0.41%

CISA KEVNot currently listed

Published2025-11-21

Last modified2026-10-19

CVSS vectorCVSS: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

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.

Weakness classification

CWE-129: Improper Validation of Array Index

Primary references

security-advisories@github.com — Patch
security-advisories@github.com — Issue Tracking, Patch, Vendor Advisory
security-advisories@github.com — Issue Tracking
security-advisories@github.com — Mitigation, Vendor Advisory