HIGH 8.7 NVD
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 processor for Cohere2 Vision models witho
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.
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-
This high severity vulnerability with a CVSS score of 8.7 was published on 2026-11-13 via NVD.
vulnfeed aggregates 21154 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.