CVE-2026-126397

EUVD-2026-125168
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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
VulnCheckCNA
7.5 HIGH
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Base Score
CVSS 3.x
EPSS Score
Percentile: 51.95%
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources (CNA/ADP records, vendor advisories, Enginsight analysis).
VendorProductVersionSource
vllmvllm
0.10.1 ≤
𝑥
< 0.31.0
CNA
Common Weakness Enumeration
Vulnerability Media Exposure
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