Vulnerability · Published Oct 5, 2026 · Assigned by GitHub_M
CVE-2026-105758vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
Medium 5.3
In plain English
A medium-severity resource allocation without limits in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 23% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.30.0 | GHSA-x6mc-67gf-chw4 |
| PyPI | vllm | 0.30.0 | PYSEC-2026-4310 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.24.0, < 0.30.0 |
Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/56729 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45 x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 x_refsource_MISC