vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.

Attack Vector Network

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction None

Vulnerable System Confidentiality Impact None

Vulnerable System Integrity Impact None

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact None

Integrity Impact None

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Key SSVC decision points have not yet been added.

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
vllm-project vllm unaffected
Version Status Constraints
0.10.1 affected < 0.31.0
0.31.0 unaffected —

No data.

No data.

No data.

Project Subscriptions

Vendors Products
Vllm Subscribe
Vllm Subscribe
Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/vllm-project/vllm/commit/f6326f53bda46898a331c2d24500332c285d9a2b cve-icon cve-icon
https://github.com/vllm-project/vllm/security/advisories/GHSA-9g3c-x747-c6wr cve-icon cve-icon
https://www.vulncheck.com/advisories/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches cve-icon cve-icon
History

Fri, 13 Nov 2026 09:45:00 +0000

Type Values Removed Values Added
Description vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.
Title vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
First Time appeared Vllm
Vllm vllm
Weaknesses CWE-400
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
References
Metrics cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 8.7, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-11-13T09:35:50.274Z

Reserved: 2026-11-10T21:30:16.910Z

Link: CVE-2026-126397

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Awaiting Analysis

Published: 2026-11-13T10:17:43.923

Modified: 2026-11-13T10:17:44.050

Link: CVE-2026-126397

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses