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 breakdown
CVSS 4.0
Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
Low
User Interaction
None
Confidentiality (Vulnerable System)
None
Integrity (Vulnerable System)
None
Availability (Vulnerable System)
High
Confidentiality (Subsequent System)
None
Integrity (Subsequent System)
None
Availability (Subsequent System)
High
Affected products
- vllm-project / vllm>= 0.5.5, < 0.11.1 – >= 0.5.5, < 0.11.1