CVE 8.3 HIGH

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs_CVE-2025-62372

8.3 / 10
HIGH
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

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.

Basic Information

ID CVE-2025-62372
Source GitHub_M
Published Nov 21, 2025 at 01:22

Affected Product

Vendor vllm-project
Product vllm
Version >= 0.5.5, < 0.11.1
Affected Versions vllm-project vllm >= 0.5.5, < 0.11.1

CWE Classification

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.