CVE-2026-126397vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
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.
Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.
Affected products and versions
| Vendor | Product | Versions | |
|---|---|---|---|
| vllm-project | vllm | 0.10.1 – < 0.31.0, fixed 0.31.0 |
References and patches
- GitHub Security Advisory (GHSA-9g3c-x747-c6wr) vendor-advisory
- Patch Commit patch
- VulnCheck Advisory: vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches third-party-advisory