CVE-2026-126397

Source
https://cve.org/CVERecord?id=CVE-2026-126397
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-126397.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-126397
Aliases
  • GHSA-9g3c-x747-c6wr
Published
2026-11-13T09:35:50Z
Modified
2026-11-15T02:46:12Z
Severity
  • 8.7 (High) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N CVSS Calculator
Summary
vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
Details

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.

Database specific
{
    "cna_assigner": "VulnCheck",
    "cwe_ids": [
        "CWE-400"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/126xxx/CVE-2026-126397.json"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Database specific
Show details
{
    "extracted_events": [
        {
            "range": [
                {
                    "introduced": "0.10.1"
                },
                {
                    "fixed": "0.31.0"
                }
            ],
            "source": "AFFECTED_FIELD",
            "strategy": "StandardRange"
        },
        {
            "range": [
                {
                    "fixed": "f6326f53bda46898a331c2d24500332c285d9a2b"
                }
            ],
            "source": "REFERENCES_COMMIT"
        }
    ]
}

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-126397.json"