CVE-2026-69147
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
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.
CVSS Vector Breakdown
AV:NAttack VectorAC:LAttack ComplexityPR:LPrivileges RequiredUI:NUser InteractionS:UScopeC:NConfidentialityI:NIntegrityA:HAvailabilityWeaknesses
Affected Products
Exploitability
Attack Graph
Click technique nodes for MITRE ATT&CK details · drag to pan · Ctrl/⌘ + scroll to zoom, or go fullscreen.
MITRE ATT&CK
1 techniqueReferences
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-69147 and every CVE in our database. Create a free account — no credit card required.
Create Free Account