CVE-2025-62372 – vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

CVE ID : CVE-2025-62372

Published : Nov. 21, 2025, 2:15 a.m. | 59 minutes ago

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.

Severity: 8.3 | HIGH

Visit the link for more details, such as CVSS details, affected products, timeline, and more…