Resource exhaustion in Vllm
CVE-2026-105758
- CVSS v3
- 5.3 Medium
- Public exploits
- None known
- EPSS
- 0.003 · 23.5th percentile
- Published
- 2026-10-05
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.
- Attack Vector
- Network
AV:N - Attack Complexity
- Low
AC:L - Privileges Required
- None
PR:N - User Interaction
- None
UI:N - Scope
- Unchanged
S:U - Confidentiality
- None
C:N - Integrity
- None
I:N - Availability
- Low
A:L
EPSS exploit prediction
EPSS 0.003, 23.5th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.24.0, < 0.30.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4 (Mitigation, Vendor Advisory)
- https://github.com/vllm-project/vllm/pull/56729 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45 (Patch)
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 (Release Notes)