CVE-2025-62372
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.
- Affected products
- Vllm
- Vllm
- < 0.11.1
- Fix
- Available
- CVSS 4.0
- 8.3 HIGH
- CVSS 3.1
- 6.5 MEDIUM
- EPSS
- 0.4% (30th percentile)
- Weakness
- CWE-129
- NVD status
- Analyzed
- Published
- 2025-11-21
CVE-2025-62372 at NVD
No indexed exploits for CVE-2025-62372 yet
Our index is partial: it proves presence, never absence
No exploit for CVE-2025-62372 has been indexed yet. Our index is built from live traffic and upstream syncs, so this page can only say what it knows — not that no exploit exists.