CVE-2025-62372
MEDIUMDescription
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.
How to fix
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Exploit Intelligence
Low risk: more likely to be exploited than 25% of all known CVEs.
References
Related Vulnerabilities
Other CWE-129 vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2021-35592 | Medium | 6.3 | 51% | - | Fix |
| CVE-2021-35598 | Medium | 6.3 | 50% | - | Fix |
| CVE-2021-35594 | Medium | 6.3 | 50% | - | Fix |
| CVE-2022-35737 | High | 7.5 | 19% | - | Fix |
| CVE-2014-6317 | High | 7.1 | 18% | - | - |
| CVE-2023-40477 | High | 7.8 | 13% | - | Fix |
Embed a live status badge for CVE-2025-62372
Markdown
[](https://tridentstack.com/cve/CVE-2025-62372)HTML
<a href="https://tridentstack.com/cve/CVE-2025-62372"><img src="https://tridentstack.com/cve/badge/CVE-2025-62372.svg" alt="CVE-2025-62372"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
Start freeThis product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2025-12-04.