CVE-2026-105760
EUVD-2026-9285105.10.2026, 23:17
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.Enginsight
Affected Products (NVD)
| Vendor | Product | Version |
|---|---|---|
| vllm | vllm | 0.23.0 ≤ 𝑥 < 0.30.0 |
𝑥
= Vulnerable software versions