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.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | >= 0.24.0, < 0.30.0 | 0.30.0 |
Affected products
4- Range: 0.24.0 to 0.30.0
- Range: 0.24.0 to 0.30.0
Patches
Vulnerability mechanics
References
5- github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45nvdPatchWEB
- github.com/vllm-project/vllm/pull/56729nvdIssue TrackingPatchWEB
- github.com/advisories/GHSA-x6mc-67gf-chw4ghsaADVISORY
- github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4nvdMitigationVendor AdvisoryWEB
- github.com/vllm-project/vllm/releases/tag/v0.30.0nvdRelease NotesWEB
News mentions
1- VLLM: Batch of 11 Medium-Severity Vulnerabilities Disclosed TogetherVypr Intelligence · Oct 6, 2026