CVE-2026-69147
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
Using vllm by vllm-project?
Get instant alerts when new vulnerabilities affect vllm - before attackers find them.
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.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet. What the record does show:
Patch and advisory references
References (4)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- LOW
- Privileges
- LOW
- User Interaction
- NONE
- Scope
- UNCHANGED
- Confidentiality
- NONE
- Integrity
- NONE
- Availability
- HIGH
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.