CyberRota Analysis
AI-GeneratedThe vulnerability affects the vLLM inference engine for large language models, specifically in versions 0.24.0 to 0.30.0, where the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes allow unauthenticated users to submit excessive request-level values for video processing parameters. This can lead to excessive memory consumption and potential termination of the API process due to unregulated handling of attacker-controlled video input. Organizations using affected versions should prioritize upgrading to version 0.30.0 to mitigate the risk of service disruption.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD 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.
Related CVEs
Other vulnerabilities affecting the same vendor(s)