Disclosure summary
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.
Source-reported weakness categories
CWE-400, CWE-770
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-69147
Open original source · Updated Oct 07, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
| Vendor | Product / association | Version / bounds |
|---|---|---|
| vllm | vllm | * {"versionEndExcluding":"0.28.0"} |
Original records & references
- NIST NVD record
- CVE Program record
- github.com — Patch
- github.com — Patch
- github.com — Issue Tracking, Patch
- github.com — Exploit, Vendor Advisory
- github.com — Exploit, Vendor Advisory
PUBLISHED 2026-09-16T14:17:11-04:00
MODIFIED 2026-10-07T10:16:57-04:00
INGESTED 2026-10-10T20:25:12-04:00