Medium severity · published Nov 21, 2025
CVE-2025-62372
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
6.5
CVSS
0.4%
EPSS
No
On KEV
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 vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 35% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
>= 0.5.5, < 0.11.1 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-62372
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-62372
Patch
https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
Issue Tracking
https://github.com/vllm-project/vllm/pull/27204
Issue Tracking
https://github.com/vllm-project/vllm/pull/6613
Mitigation
https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw
More from vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints