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.

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