CVE-2025-62372

Source
https://cve.org/CVERecord?id=CVE-2025-62372
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-62372.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2025-62372
Aliases
Related
Published
2025-11-21T01:22:37.121Z
Modified
2026-04-10T05:32:59.440026Z
Severity
  • 8.3 (High) CVSS_V4 - CVSS: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 Calculator
Summary
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
Details

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.

Database specific
{
    "cwe_ids": [
        "CWE-129"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62372.json",
    "cna_assigner": "GitHub_M"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events

Affected versions

v0.*
v0.10.0
v0.10.0rc1
v0.10.0rc2
v0.10.1rc1
v0.10.2rc1
v0.10.2rc2
v0.11.0rc1
v0.11.1rc0
v0.11.1rc1
v0.11.1rc2
v0.11.1rc3
v0.11.1rc4
v0.11.1rc5
v0.11.1rc6
v0.5.5
v0.6.0
v0.6.1
v0.6.1.post1
v0.6.1.post2
v0.6.2
v0.6.3
v0.6.3.post1
v0.6.4
v0.6.4.post1
v0.6.5
v0.6.6
v0.6.6.post1
v0.7.0
v0.7.1
v0.7.2
v0.7.3
v0.8.0rc1
v0.8.0rc2
v0.8.1
v0.8.2
v0.8.3rc1
v0.8.4
v0.9.0
v0.9.1
v0.9.1rc1
v0.9.1rc2
v0.9.2rc1

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-62372.json"