CVE-2026-105760

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2026-105760
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-105760.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-105760
Aliases
Published
2026-10-05T23:01:54Z
Modified
2026-10-06T10:45:55Z
Severity
  • 5.3 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L CVSS Calculator
Summary
vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Details

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.

Database specific 
{
    "cna_assigner":  "GitHub_M",
    "cwe_ids":  [
        "CWE-400"
    ],
    "osv_generated_from":  "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105760.json"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Introduced
78743ab5bffd381e88f97e1c8ba20473b0ae6d75
Fixed
9ed533eb4adfe48aef7e569a08daeccd2a773fed
Database specific
Show details 
{
    "extracted_events":  [
        {
            "introduced":  "0.23.0rc2"
        },
        {
            "fixed":  "0.30.0"
        }
    ],
    "source":  "AFFECTED_FIELD"
}

Database specific

source 
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-105760.json"