VulnWatch VulnWatch
← Back to dashboard
High nvd · CVE-2026-126397

CVE-2026-126397: vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face p

Published Nov 13, 2026 CVSS 8.7

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.

Affected AI Products

hugging face cohere vllm
Get the weekly digest. Every Monday: top AI security stories of the week. Free.