vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation (CVE-2026-69147) | HOL Guard CVE

Unknown severity · Source severity not reportedCVE-2026-69147

vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation

Answer in brief

CVE-2026-69147 records a Unknown severity vulnerability in vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Sep 16, 2026Updated Sep 16, 2026Source checked Sep 16, 2026First seen by HOL Sep 16, 2026Material review Sep 16, 2026

Upstream Advisory

Key facts

Risk: Unknown severitySource severity not reported
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Not reported

Why this deserves its current priority

A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
vllm-project/vllmgeneric	< 0.28.0	Not reported

Recommended response

Check inventory. Check lockfiles and deployed manifests for vllm-project/vllm.
Review the reported fix. Monitor this advisory for an available fix and review any installs of the affected package.

Evidence timeline and material changes

Published upstream
Sep 16, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Sep 16, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Sep 16, 2026

Sources and claim methodology

Upstream source 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.

Quoted source text, attributed separately from HOL analysis.