Resource exhaustion in Vllm-Project Vllm
CVE-2026-105760
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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Vllm-Project Vllm — versions >= 0.23.0rc2, < 0.30.0
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-105760?
- CVE-2026-105760 is a medium-severity vulnerability in Vllm-Project Vllm, classified under Uncontrolled Resource Consumption. CVSS score: 5.3/10. Published 2026-10-05.
- How severe is CVE-2026-105760?
- Medium severity. CVSS v3 base score is 5.3 out of 10.