CVE-2026-109228

SGLang versions through 0.5.21 are vulnerable to a resource budget bypass in the GLM-V video processing logic. By supplying arbitrary values for fps, max_frames, max_tokens_per_frame, and max_image_tokens within the video_url object, a remote attacker can force glm4v.py to decode every frame of a...

EUVD-2026-97434

SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, maxframes, maxtokensperframe and maximagetokens in the videourl object. Attackers can set these values arbitrarily high so glm4v.py decode...

GHSA-X6MC-67GF-CHW4 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

Summary An unauthenticated remote attacker can exhaust the memory of the vLLM API-server process by raising the request-level mediaiokwargs.video.maxframes and fps knobs on any deployment serving a Qwen2-VL or Qwen3-VL model. 74 extra bytes of JSON took the server's peak RSS from 2 271 MiB to 13...

CVE-2026-105758

The vLLM inference engine (versions 0.24.0 through 0.30.0 ) is vulnerable to a resource exhaustion issue within the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes. The software fails to enforce server-side ceilings on media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields prov...