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.
Metrics
CVSS 3.1 7.5/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HWeakness enumeration
Affected software
Source: the vendor's advisory (CNA). NVD analysis pending.
No affected versions have been published.
Timeline
- Published
- Nov 13, 2026
- Last modified
- Nov 13, 2026
- NVD status
- Awaiting Analysis