CVE & CISA-KEV Catalog

CVE-2025-62372

MEDIUM
6.5
CVSS v3
NVD

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.

How to fix

Remediation Available
registry.redhat.io/rhaiis/vllmRed Hat / RHEL
Fixed in:rocm-rhel9@sha256:c5efe40fa2a6e98d7d3d6676befff0dbbd87b2887769bb7e5856c5b0b0ada125_amd64RHSA-2025:23449
Fixed in:cuda-rhel9@sha256:dcb9d1cd005c40b6db6f893e56419e383b9dcc0d38315605cb1457e2af5354f7_amd64RHSA-2026:3461
Fixed in:cuda-rhel9@sha256:fa844e16d06e871f1a5dbc2fd5b3882d28112eee8d6bee601d94c96295c5e24f_arm64RHSA-2026:3461
Fixed in:tpu-rhel9@sha256:64796b48c68d31973a08e22c9530c39b1bc3ba9f376bbefa57643ef0fc857534_amd64RHSA-2025:23209
Fixed in:rocm-rhel9@sha256:53007894763e03f609c35c727cb738db3c2130b19fa0e1069c24240e0870fb7a_amd64RHSA-2026:3462
Fixed in:rocm-rhel9@sha256:e3b3efcdd86f60b90664a249d45918b2ac5f45bae5eed5399e310d63e878b287_amd64RHSA-2025:23205
Fixed in:cuda-rhel9@sha256:7b04c0154c486aa7dd103ddeaf6bea7b9851859c33a4b979a85261a44a7b77f2_amd64RHSA-2025:23204
Fixed in:cuda-rhel9@sha256:f0ab1b678e9447eae4b6b2fe5c58531aa8524133db157f196726164e4dc20492_arm64RHSA-2025:23204
registry.redhat.io/rhaiis/vllmRocky
Fixed in:rocm-rhel9@sha256:c5efe40fa2a6e98d7d3d6676befff0dbbd87b2887769bb7e5856c5b0b0ada125_amd64RHSA-2025:23449
Fixed in:cuda-rhel9@sha256:dcb9d1cd005c40b6db6f893e56419e383b9dcc0d38315605cb1457e2af5354f7_amd64RHSA-2026:3461
Fixed in:cuda-rhel9@sha256:fa844e16d06e871f1a5dbc2fd5b3882d28112eee8d6bee601d94c96295c5e24f_arm64RHSA-2026:3461
Fixed in:tpu-rhel9@sha256:64796b48c68d31973a08e22c9530c39b1bc3ba9f376bbefa57643ef0fc857534_amd64RHSA-2025:23209
Fixed in:rocm-rhel9@sha256:53007894763e03f609c35c727cb738db3c2130b19fa0e1069c24240e0870fb7a_amd64RHSA-2026:3462
Fixed in:rocm-rhel9@sha256:e3b3efcdd86f60b90664a249d45918b2ac5f45bae5eed5399e310d63e878b287_amd64RHSA-2025:23205
Fixed in:cuda-rhel9@sha256:7b04c0154c486aa7dd103ddeaf6bea7b9851859c33a4b979a85261a44a7b77f2_amd64RHSA-2025:23204
Fixed in:cuda-rhel9@sha256:f0ab1b678e9447eae4b6b2fe5c58531aa8524133db157f196726164e4dc20492_arm64RHSA-2025:23204

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

Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredLow
User InteractionNone
ScopeUnchanged

Impact

ConfidentialityNone
IntegrityNone
AvailabilityHigh

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Exploit Intelligence

0.33%probability of exploitation in 30 days
25thpercentile

Low risk: more likely to be exploited than 25% of all known CVEs.

References

Vendor Advisory1
Issue Tracking1

Related Vulnerabilities

Other CWE-129 vulnerabilities, ordered by exploit likelihood. View all

CVESeverityCVSSEPSSExploitedFix
CVE-2021-35592Medium6.351%-Fix
CVE-2021-35598Medium6.350%-Fix
CVE-2021-35594Medium6.350%-Fix
CVE-2022-35737High7.519%-Fix
CVE-2014-6317High7.118%--
CVE-2023-40477High7.813%-Fix
Embed a live status badge for CVE-2025-62372
CVE-2025-62372 severity badge

Markdown

[![CVE-2025-62372](https://tridentstack.com/cve/badge/CVE-2025-62372.svg)](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 free

This 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.