Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Affected products
vllm: vllm
References4
- github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f… MitigationVendor Advisory
- github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d… Patch
- github.com/vllm-project/vllm/pull/54935 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.30.0 Release Notes
Metrics
- CVSS 3.1
-
5.3
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L - EPSS — exploit probability
- 0% percentile: 23 · as of 10 November 2026
- CWE
- CWE-400
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.