High severity7.5NVD Advisory· Published Nov 13, 2026· Updated Nov 18, 2026
CVE-2026-126397
CVE-2026-126397
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
1Patches
Vulnerability mechanics
References
3News mentions
0No linked articles in our index yet.