Description
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3… ExploitVendor Advisory
- github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3… ExploitVendor Advisory
- github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b… Patch
- github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a2… Patch
- github.com/vllm-project/vllm/pull/47259 Issue TrackingPatch
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - EPSS — exploit probability
- 1% percentile: 48 · as of 8 November 2026
- CWE
- CWE-400CWE-770
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.