Vulnerability 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 Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.5.5, < 0.11.1 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9Patch
- https://github.com/vllm-project/vllm/pull/27204Issue TrackingPatchVendor Advisory
- https://github.com/vllm-project/vllm/pull/6613Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qwMitigationVendor Advisory
FAQ
What is CVE-2025-62372?
CVE-2025-62372 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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...
How severe is CVE-2025-62372?
CVE-2025-62372 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-62372?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.