CVE-2026-105760
Common Vulnerabilities and Exposures record
Summary
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.
Risk
- CVSS
- 5.3
- Severity
- MEDIUM
- Vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Timeline
- Published
- Oct 5, 2026 23:17
- Modified
- Oct 16, 2026 20:39
- Last observed
- Oct 16, 2026 23:38