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

[ Description ]Official 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.

[ Fixes ]Fixes and patches

• vllm 0.30.0Fixed version · GitHub Advisories · pip package vllm: upgrade to 0.30.0 or later (affected >= 0.24.0, < 0.30.0)
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Advisories ]Government CERT advisories

• BSI CERT-Bund5 Oct 2026WID-SEC-2026-3754

  vllm: Multiple vulnerabilities allow denial of service Translated from German

  CVE-2026-105758CVE-2026-105760CVE-2026-105759+2 more CVEs

[ Packages ]Affected open-source packages

• vllm pipAffected >= 0.24.0, < 0.30.0 · fixed in 0.30.0 · GHSA-x6mc-67gf-chw4

[ References ]References

• github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45Patch
• github.com/vllm-project/vllm/pull/56729Issue TrackingPatch
• github.com/vllm-project/vllm/releases/tag/v0.30.0Release Notes
• github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4MitigationVendor Advisory