CVE-2026-126397

vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches

Published Nov 13, 2026 CVSS 4.0 · 8.7 High EPSS n/a KEV · Not listed

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.

Analysis

No analysis available yet

Affected Products

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 available yet.

Remediation

No remediation available yet

Tracking

Advisories

No advisories available

Metrics

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.

References

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

History

Nov 13, 2026 9:45 AM Description updated. Title updated. First appearance in the feed. Weaknesses updated. Affected versions updated. Affected vendors updated. Added references. Scoring metrics updated View changes

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		https://github.com/vllm-project/vllm/commit/f6326f53bda46898a331c2d24500332c285d9a2b https://github.com/vllm-project/vllm/security/advisories/GHSA-9g3c-x747-c6wr https://www.vulncheck.com/advisories/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches
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'}`