p PatchFirst

CVE-2026-105758

CVE-2026-105758 · vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

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. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler to decode every frame selected from attacker-controlled video input, consume disproportionate frontend memory, and potentially terminate the API process before scheduling or admission control. The Rust frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version 0.30.0.

CVSS 5.3 · Medium · EPSS 0.3% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.24.0, < 0.30.0: Affected

    No fix published

  • vllm PyPI

    Versions
    • 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: ≥ 0.24.0, < 0.30.0

    Update to 0.30.0

Original sources

Check your server →