CVE-2025-62372
Severity CVSS v4.0:
HIGH
Type:
Unavailable / Other
Publication date:
21/11/2025
Last modified:
21/11/2025
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.
Impact
Base Score 4.0
8.30
Severity 4.0
HIGH