Resource exhaustion in Vllm-Project Vllm
CVE-2026-105758
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Vllm-Project Vllm — versions >= 0.24.0, < 0.30.0
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-105758?
- CVE-2026-105758 is a medium-severity vulnerability in Vllm-Project Vllm, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 5.3/10. Published 2026-10-05.
- How severe is CVE-2026-105758?
- Medium severity. CVSS v3 base score is 5.3 out of 10.