CVE-2026-105760
vllm-project vllm
Published 5 Oct 2026 · updated 6 Oct 2026 · Undergoing Analysis
5.3 Medium · CVSS 3.1, github.com
Description
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.