CVE-2026-55514

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2026-55514
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-55514.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-55514
Aliases
Downstream
Published
2026-07-06T20:07:40.405Z
Modified
2026-07-13T07:26:12.683023961Z
Severity
  • 7.1 (High) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N CVSS Calculator
Summary
vLLM denial of service via prompt embeds on M-RoPE models
Details

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

Database specific 
{
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/55xxx/CVE-2026-55514.json",
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
        "CWE-617"
    ]
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Introduced
4fd9d6a85c00ac0186aa9abbeff73fc2ac6c721e
Fixed
217c64a976869883fcf0c52a8cf8bc3c954d285b
Fixed
470229c37efaf69c86e8bc97482b0b1ff7551c65
Database specific 
{
    "source": [
        "CPE_RANGE",
        "REFERENCES"
    ],
    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
    "extracted_events": [
        {
            "introduced": "0.12.0"
        },
        {
            "fixed": "0.24.0"
        }
    ]
}

Database specific

source 
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-55514.json"