p PatchFirst

CVE-2026-105760

CVE-2026-105760 · vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 5.3 · Medium · EPSS 0.3% · Public exploit · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.23.0rc2, < 0.30.0: Affected

    No fix published

  • vllm PyPI

    Versions
    • 0.23.0
    • 0.24.0
    • 0.25.0
    • 0.25.1
    • 0.26.0
    • 0.27.0
    • 0.27.1
    • 0.28.0
    • 0.29.0
    Affected ranges
    • ECOSYSTEM: ≥ 0.23.0rc2, < 0.30.0

    Update to 0.30.0

Original sources

Check your server →