CVE-2026-126397
vLLM from 0.10.1 before 0.31.0 forwards a request-controlled …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm/commit/f6326f53bda46898a331c2d24500332c285d9a2b
- github.com/vllm-project/vllm/security/advisories/GHSA-9g3c-x747-c6wr
- www.vulncheck.com/advisories/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches
- nvd.nist.gov/vuln/detail/CVE-2026-126397
- cve.org/CVERecord?id=CVE-2026-126397
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.