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.

CVSS 4.0

8.3CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

CVSS 3.1

6.5CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS

0.4% chance of exploitation in the next 30 days; higher than 34% of CVEs (scores of 2026-10-25)

CWE

CWE-129

Published

2025-11-21

Modified

2026-10-19

Record from

the NVD, synced 2026-10-19

Affected

• vllm:vllm

Packages (OSV)

References

• https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
• https://github.com/vllm-project/vllm/pull/27204
• https://github.com/vllm-project/vllm/pull/6613
• https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw

Check your stackJSON