VYPR
Medium severity5.3NVD Advisory· Published Oct 5, 2026· Updated Oct 8, 2026

CVE-2026-105758

CVE-2026-105758

Description

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.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
vllmPyPI
>= 0.24.0, < 0.30.00.30.0

Affected products

4

Patches

Vulnerability mechanics

References

5

News mentions

1